Recently, Large Language Models (LLMs) and Vision Language Models (VLMs) have demonstrated aptitude as potential substitutes for human participants in experiments testing psycholinguistic phenomena. However, an understudied question is to what extent models that only have access to vision and text modalities are able to implicitly understand sound-based phenomena via abstract reasoning from orthography and imagery alone. To investigate this, we analyse the ability of VLMs and LLMs to demonstrate sound symbolism (i.e., to recognise a non-arbitrary link between sounds and concepts) as well as their ability to “hear” via the interplay of the language and vision modules of open and closed-source multimodal models. We perform multiple experiments, including replicating the classic Kiki-Bouba and Mil-Mal shape and magnitude symbolism tasks and comparing human judgements of linguistic iconicity with that of LLMs. Our results show that VLMs demonstrate varying levels of agreement with human labels, and more task information may be required for VLMs versus their human counterparts for in silico experimentation. We additionally see through higher maximum agreement levels that Magnitude Symbolism is an easier pattern for VLMs to identify than Shape Symbolism, and that an understanding of linguistic iconicity is highly dependent on model size.

Machine Translation (MT) has developed rapidly since the release of Large Language Models and current MT evaluation is performed through comparison with reference human translations or by predicting quality scores from human-labeled data. However, these mainstream evaluation methods mainly focus on fluency and factual reliability, whilst paying little attention to figurative quality. In this paper, we investigate the figurative quality of MT and propose a set of human evaluation metrics focused on the translation of figurative language. We additionally present a multilingual parallel metaphor corpus generated by post-editing. Our evaluation protocol is designed to estimate four aspects of MT: Metaphorical Equivalence, Emotion, Authenticity, and Quality. In doing so, we observe that translations of figurative expressions display different traits from literal ones.

Text ranking has witnessed significant advancements, attributed to the utilization of dual-encoder enhanced by Pre-trained Language Models (PLMs). Given the proliferation of available PLMs, selecting the most effective one for a given dataset has become a non-trivial challenge. As a promising alternative to human intuition and brute-force fine-tuning, Transferability Estimation (TE) has emerged as an effective approach to model selection. However, current TE methods are primarily designed for classification tasks, and their estimated transferability may not align well with the objectives of text ranking. To address this challenge, we propose to compute the expected rank as transferability, explicitly reflecting the model’s ranking capability. Furthermore, to mitigate anisotropy and incorporate training dynamics, we adaptively scale isotropic sentence embeddings to yield an accurate expected rank score. Our resulting method, Adaptive Ranking Transferability (AiRTran), can effectively capture subtle differences between models. On challenging model selection scenarios across various text ranking datasets, it demonstrates significant improvements over previous classification-oriented TE methods, human intuition, and ChatGPT with minor time consumption.

While LLMs demonstrate impressive capabilities in musical knowledge, we find that music reasoning is still an unsolved task.We introduce ChatMusician, an open-source large language model (LLM) that integrates intrinsic musical abilities. It is based on continual pre-training and finetuning LLaMA2 on a text-compatible music representation, ABC notation, and the music is treated as a second language.ChatMusician can understand and generate music with a pure text tokenizer without external multi-modal neural structures or tokenizers. Interestingly, endowing musical abilities does not harm language abilities, even achieving a slightly higher MMLU score.ChatMusician is capable of composing well-structured, full-length music, condition on texts, chords, melodies, motifs, musical forms, etc.On our meticulously curated college-level music understanding benchmark, MusicTheoryBench, ChatMusician surpasses LLaMA2 and GPT-3.5 by a noticeable margin. We show that ChatMusician preserves or even surpasses the original LLaMA2 7B’s language abilities by evaluating on MMLU benchmark.Our work reveals that LLMs can be an excellent compressor for music, which can be seen as humanity’s creative language, but there remains significant territory to be conquered.We release our 5B token music-language corpora MusicPiles, the collected MusicTheoryBench, code, model and demo.

The advancement of large language models (LLMs) has enhanced the ability to generalize across a wide range of unseen natural language processing (NLP) tasks through instruction-following.Yet, their effectiveness often diminishes in low-resource languages like Chinese, exacerbated by biased evaluations from data leakage, casting doubt on their true generalizability to new linguistic territories. In response, we introduce the Chinese Instruction-Following Benchmark (**CIF-Bench**), designed to evaluate the zero-shot generalizability of LLMs to the Chinese language. CIF-Bench comprises 150 tasks and 15,000 input-output pairs, developed by native speakers to test complex reasoning and Chinese cultural nuances across 20 categories. To mitigate data contamination, we release only half of the dataset publicly, with the remainder kept private, and introduce diversified instructions to minimize score variance, totaling 45,000 data instances.Our evaluation of 28 selected LLMs reveals a noticeable performance gap, with the best model scoring only 52.9%, highlighting the limitations of LLMs in less familiar language and task contexts.This work not only uncovers the current limitations of LLMs in handling Chinese language tasks but also sets a new standard for future LLM generalizability research, pushing towards the development of more adaptable, culturally informed, and linguistically diverse models.

Multi-modal information retrieval (MMIR) is a rapidly evolving field where significant progress has been made through advanced representation learning and cross-modality alignment research, particularly in image-text pairing.However, current benchmarks for evaluating MMIR performance on image-text pairings overlook the scientific domain, which has a notable gap with the generic data since the caption of scientific charts and tables usually describes the analysis of experimental results or scientific principles in contrast to human activity or scenery depicted in generic images.To bridge this gap, we develop a scientific domain-specific MMIR benchmark (SciMMIR) by leveraging open-access research paper corpora to extract data relevant to the scientific domain. This benchmark comprises 530K meticulously curated image-text pairs, extracted from figures and tables with detailed captions from scientific documents.We further annotate the image-text pairs with a two-level subset-subcategory hierarchy to facilitate a more comprehensive evaluation of the baselines. We conduct zero-shot and fine-tuned evaluations on prominent multi-modal image-captioning and visual language models, such as CLIP, BLIP, and BLIP-2.Our findings offer critical insights for MMIR in the scientific domain, including the impact of pre-training and fine-tuning settings and the effects of different visual and textual encoders.

Automatic evaluation of generated textual content presents an ongoing challenge within the field of NLP. Given the impressive capabilities of modern language models (LMs) across diverse NLP tasks, there is a growing trend to employ these models in creating innovative evaluation metrics for automated assessment of generation tasks. This paper investigates a pivotal question: Do language model-driven evaluation metrics inherently exhibit bias favoring texts generated by the same underlying language model? Specifically, we assess whether prominent LM-based evaluation metrics (e.g. BARTScore, T5Score, and GPTScore) demonstrate a favorable bias toward their respective underlying LMs in the context of summarization tasks. Our findings unveil a latent bias, particularly pronounced when such evaluation metrics are used in a reference-free manner without leveraging gold summaries. These results underscore that assessments provided by generative evaluation models can be influenced by factors beyond the inherent text quality, highlighting the necessity of developing more reliable evaluation protocols in the future.

The long-standing one-to-many problem of gold standard responses in open-domain dialogue systems presents challenges for automatic evaluation metrics. Though prior works have demonstrated some success by applying powerful Large Language Models (LLMs), existing approaches still struggle with the one-to-many problem, and exhibit subpar performance in domain-specific scenarios. We assume the commonsense reasoning biases within LLMs may hinder their performance in domain-specific evaluations. To address both issues, we propose a novel framework SLIDE (Small and Large Integrated for Dialogue Evaluation), that leverages both a small, specialised model (SLM), and LLMs for the evaluation of open domain dialogues. Our approach introduces several techniques: (1) Contrastive learning to differentiate between robust and non-robust response embeddings; (2) A novel metric for semantic sensitivity that combines embedding cosine distances with similarity learned through neural networks, and (3) A strategy for incorporating the evaluation results from both the SLM and LLMs. Our empirical results demonstrate that our approach achieves state-of-the-art performance in both the classification and evaluation tasks, and additionally the SLIDE evaluator exhibits better correlation with human judgements. Our code is available at https://github.com/hegehongcha/SLIDE-ACL2024.

Data contamination in model evaluation has become increasingly prevalent with the growing popularity of large language models. It allows models to “cheat” via memorisation instead of displaying true capabilities. Therefore, contamination analysis has become an crucial part of reliable model evaluation to validate results. However, existing contamination analysis is usually conducted internally by large language model developers and often lacks transparency and completeness. This paper presents an extensive data contamination report for over 15 popular large language models across six popular multiple-choice QA benchmarks. We also introduce an open-source pipeline that enables the community to perform contamination analysis on customised data and models. Our experiments reveal varying contamination levels ranging from 1% to 45% across benchmarks, with the contamination degree increasing rapidly over time. Performance analysis of large language models indicates that data contamination does not necessarily lead to increased model metrics: while significant accuracy boosts of up to 14% and 7% are observed on contaminated C-Eval and Hellaswag benchmarks, only a minimal increase is noted on contaminated MMLU. We also find larger models seem able to gain more advantages than smaller models on contaminated test sets.

Rigour is crucial for scientific research as it ensures the reproducibility and validity of results and findings. Despite its importance, little work exists on modelling rigour computationally, and there is a lack of analysis on whether these criteria can effectively signal or measure the rigour of scientific papers in practice. In this paper, we introduce a bottom-up, data-driven framework to automatically identify and define rigour criteria and assess their relevance in scientific writing. Our framework includes rigour keyword extraction, detailed rigour definition generation, and salient criteria identification. Furthermore, our framework is domain-agnostic and can be tailored to the evaluation of scientific rigour for different areas, accommodating the distinct salient criteria across fields. We conducted comprehensive experiments based on datasets collected from different domains (e.g. ICLR, ACL) to demonstrate the effectiveness of our framework in modelling rigour. In addition, we analyse linguist patterns of rigour, revealing that framing certainty is crucial for enhancing the perception of scientific rigour, while suggestion certainty and probability uncertainty diminish it.

Commonsense knowledge is crucial to many natural language processing tasks. Existing works usually incorporate graph knowledge with conventional graph neural networks (GNNs), resulting in a sequential pipeline that compartmentalizes the encoding processes for textual and graph-based knowledge. This compartmentalization does, however, not fully exploit the contextual interplay between these two types of input knowledge. In this paper, a novel context-aware graph-attention model (Context-aware GAT) is proposed, designed to effectively assimilate global features from relevant knowledge graphs through a context-enhanced knowledge aggregation mechanism. Specifically, the proposed framework employs an innovative approach to representation learning that harmonizes heterogeneous features by amalgamating flattened graph knowledge with text data. The hierarchical application of graph knowledge aggregation within connected subgraphs, complemented by contextual information, to bolster the generation of commonsense-driven dialogues is analyzed. Empirical results demonstrate that our framework outperforms conventional GNN-based language models in terms of performance. Both, automated and human evaluations affirm the significant performance enhancements achieved by our proposed model over the concept flow baseline.

As the cultural heritage sector increasingly adopts technologies like Retrieval-Augmented Generation (RAG) to provide more personalised search experiences and enable conversations with collections data, the demand for specialised evaluation datasets has grown. While end-to-end system testing is essential, it’s equally important to assess individual components. We target the final, answering task, which is well-suited to Machine Reading Comprehension (MRC). Although existing MRC datasets address general domains, they lack the specificity needed for cultural heritage information. Unfortunately, the manual creation of such datasets is prohibitively expensive for most heritage institutions. This paper presents a cost-effective approach for generating domain-specific MRC datasets with increased difficulty using Reinforcement Learning from Human Feedback (RLHF) from synthetic preference data. Our method leverages the performance of existing question-answering models on a subset of SQuAD to create a difficulty metric, assuming that more challenging questions are answered correctly less frequently. This research contributes: (1) A methodology for increasing question difficulty using PPO and synthetic data; (2) Empirical evidence of the method’s effectiveness, including human evaluation; (3) An in-depth error analysis and study of emergent phenomena; and (4) An open-source codebase and set of three llama-2-chat adapters for reproducibility and adaptation.

This paper describes a partial reproduction of the work titled “Generating Fact Checking Explanations” by Atanasova et al. (2020) as part of the ReproHum element within the ReproNLP shared task, aimed at reproducing findings in NLP research related to human evaluation. The task investigates whether NLP research is becoming more or less reproducible over time. Following instructions from the task organizers and the original authors, we gathered relative rankings for three fact-checking explanations (including a gold standard and outputs from two models) for 40 inputs based on the criterion of Coverage. Our reproduction and reanalysis of the original study’s raw results support the initial findings, showing similar patterns between the original work and our reproduction. Though we observed slight variations from the original results, our findings align with the main conclusions drawn by the original authors regarding the effectiveness of their proposed models.

Lay summarisation aims to produce summaries of scientific articles that are comprehensible to non-expert audiences. However, previous work assumes a one-size-fits-all approach, where the content and style of the produced summary are entirely dependent on the data used to train the model. In practice, audiences with different levels of expertise will have specific needs, impacting what content should appear in a lay summary and how it should be presented. Aiming to address this, we propose ATLAS, a novel abstractive summarisation approach that can control various properties that contribute to the overall “layness” of the generated summary using targeted control attributes. We evaluate ATLAS on a combination of biomedical lay summarisation datasets, where it outperforms state-of-the-art baselines using mainstream summarisation metrics.Additional analyses provided on the discriminatory power and emergent influence of our selected controllable attributes further attest to the effectiveness of our approach.

This paper presents the setup and results of the second edition of the BioLaySumm shared task on the Lay Summarisation of Biomedical Research Articles, hosted at the BioNLP Workshop at ACL 2024. In this task edition, we aim to build on the first edition’s success by further increasing research interest in this important task and encouraging participants to explore novel approaches that will help advance the state-of-the-art. Encouragingly, we found research interest in the task to be high, with this edition of the task attracting a total of 53 participating teams, a significant increase in engagement from the previous edition. Overall, our results show that a broad range of innovative approaches were adopted by task participants, with a predictable shift towards the use of Large Language Models (LLMs).

Metaphor is a prominent linguistic device in human language and literature, as they add color, imagery, and emphasis to enhance effective communication. This paper introduces a large-scale high quality annotated Chinese Metaphor Corpus, which comprises around 28K sentences drawn from a diverse range of Chinese literary sources, such as poems, prose, song lyrics, etc. To ensure the accuracy and consistency of our annotations, we introduce a comprehensive set of guidelines. These guidelines address the facets of metaphor annotation, including identifying tenors, vehicles, and grounds to handling the complexities of similes, personifications, juxtapositions, and hyperboles. Breaking tradition, our approach to metaphor generation emphasizes tenors and their distinct features rather than the conventional combination of tenors and vehicles. By integrating “ground” as a CoT (Chain of Thoughts) input, we are able to generate metaphors that resonate more with real-world intuition. We test generative models such as Belle, Baichuan, and Chinese-alpaca-33B using our annotated corpus. These models are able to generate creative and fluent metaphor sentences more frequently induced by selected samples from our dataset, demonstrating the value of our corpus for Chinese metaphor research.

Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of natural language processing tasks. However, their enormous parameter size and extremely high requirements for compute power pose challenges for their practical deployment. Recent research has revealed that specific capabilities of LLMs, such as numerical reasoning, can be transferred to smaller models through distillation. Some studies explore the potential of leveraging LLMs to perform table-based reasoning. However, there has been no prior work focusing on table reasoning skills in smaller models specifically tailored for scientific table-to-text generation tasks. In this paper, we propose a novel table-based reasoning distillation approach, with the aim of distilling LLMs into tailored smaller models. Our experimental results have shown that a 220 million parameter model (Flan-T5-base) fine-tuned using distilled data, not only achieves a significant improvement compared to traditionally fine-tuned baselines, but also surpasses specific LLMs on a scientific table-to-text generation dataset. Our code is available at https://github.com/Bernard-Yang/DistillTableCoT.

The long-standing one-to-many issue of the open-domain dialogues poses significant challenges for automatic evaluation methods, i.e., there may be multiple suitable responses which differ in semantics for a given conversational context. To tackle this challenge, we propose a novel learning-based automatic evaluation metric (CMN), which can robustly evaluate open-domain dialogues by augmenting Conditional Variational Autoencoders (CVAEs) with a Next Sentence Prediction (NSP) objective and employing Mutual Information (MI) to model the semantic similarity of text in the latent space. Experimental results on two open-domain dialogue datasets demonstrate the superiority of our method compared with a wide range of baselines, especially in handling responses which are distant to the “golden” reference responses in semantics.

Incorporating external graph knowledge into neural chatbot models has been proven effective for enhancing dialogue generation. However, in conventional graph neural networks (GNNs), message passing on a graph is independent from text, resulting in the graph representation hidden space differing from that of the text. This training regime of existing models therefore leads to a semantic gap between graph knowledge and text. In this study, we propose a novel framework for knowledge graph enhanced dialogue generation. We dynamically construct a multi-hop knowledge graph with pseudo nodes to involve the language model in feature aggregation within the graph at all steps. To avoid the semantic biases caused by learning on vanilla subgraphs, the proposed framework applies hierarchical graph attention to aggregate graph features on pseudo nodes and then attains a global feature. Therefore, the framework can better utilise the heterogeneous features from both the post and external graph knowledge. Extensive experiments demonstrate that our framework outperforms state-of-the-art (SOTA) baselines on dialogue generation. Further analysis also shows that our representation learning framework can fill the semantic gap by coagulating representations of both text and graph knowledge. Moreover, the language model also learns how to better select knowledge triples for a more informative response via exploiting subgraph patterns within our feature aggregation process. Our code and resources are available at https://github.com/tangg555/SaBART.

One noticeable trend in metaphor detection is the embrace of linguistic theories such as the metaphor identification procedure (MIP) for model architecture design. While MIP clearly defines that the metaphoricity of a lexical unit is determined based on the contrast between its contextual meaning and its basic meaning, existing work does not strictly follow this principle, typically using the aggregated meaning to approximate the basic meaning of target words. In this paper, we propose a novel metaphor detection method, which models the basic meaning of the word based on literal annotation from the training set, and then compares this with the contextual meaning in a target sentence to identify metaphors. Empirical results show that our method outperforms the state-of-the-art method significantly by 1.0% in F1 score. Moreover, our performance even reaches the theoretical upper bound on the VUA18 benchmark for targets with basic annotations, which demonstrates the importance of modelling basic meanings for metaphor detection.

Previous work in phonetically-grounded language generation has mainly focused on domains such as lyrics and poetry. In this paper, we present work on the generation of tongue twisters - a form of language that is required to be phonetically conditioned to maximise sound overlap, whilst maintaining semantic consistency with an input topic, and still being grammatically correct. We present TwistList, a large annotated dataset of tongue twisters, consisting of 2.1K+ human-authored examples. We additionally present several benchmark systems (referred to as TwisterMisters) for the proposed task of tongue twister generation, including models that both do and do not require training on in-domain data. We present the results of automatic and human evaluation to demonstrate the performance ofexisting mainstream pre-trained models in this task with limited (or no) task specific training and data, and no explicit phonetic knowledge. We find that the task of tongue twister generation is challenging for models under these conditions, yet some models are still capable of generating acceptable examples of this language type.

This paper presents the results of the shared task on Lay Summarisation of Biomedical Research Articles (BioLaySumm), hosted at the BioNLP Workshop at ACL 2023. The goal of this shared task is to develop abstractive summarisation models capable of generating “lay summaries” (i.e., summaries that are comprehensible to non-technical audiences) in both a controllable and non-controllable setting. There are two subtasks: 1) Lay Summarisation, where the goal is for participants to build models for lay summary generation only, given the full article text and the corresponding abstract as input; and2) Readability-controlled Summarisation, where the goal is for participants to train models to generate both the technical abstract and the lay summary, given an article’s main text as input. In addition to overall results, we report on the setup and insights from the BioLaySumm shared task, which attracted a total of 20 participating teams across both subtasks.

Learning logic rules for knowledge graph reasoning is essential as such rules provide interpretable explanations for reasoning and can be generalized to different domains. However, existing methods often face challenges such as searching in a vast search space (e.g., enumeration of relational paths or multiplication of high-dimensional matrices) and inefficient optimization (e.g., techniques based on reinforcement learning or EM algorithm). To address these limitations, this paper proposes a novel framework called LatentLogic to efficiently mine logic rules by controllable generation in the latent space. Specifically, to map the discrete relational paths into the latent space, we leverage a pre-trained VAE and employ a discriminator to establish an energy-based distribution. Additionally, we incorporate a sampler based on ordinary differential equations, enabling the efficient generation of logic rules in our approach. Extensive experiments on benchmark datasets demonstrate the effectiveness and efficiency of our proposed method.

Transferability estimation has been attached to great attention in the computer vision fields. Researchers try to estimate with low computational cost the performance of a model when transferred from a source task to a given target task. Considering the effectiveness of such estimations, the communities of natural language processing also began to study similar problems for the selection of pre-trained language models. However, there is a lack of a comprehensive comparison between these estimation methods yet. Also, the differences between vision and language scenarios make it doubtful whether previous conclusions can be established across fields. In this paper, we first conduct a thorough survey of existing transferability estimation methods being able to find the most suitable model, then we conduct a detailed empirical study for the surveyed methods based on the GLUE benchmark. From qualitative and quantitative analyses, we demonstrate the strengths and weaknesses of existing methods and show that H-Score generally performs well with superiorities in effectiveness and efficiency. We also outline the difficulties of consideration of training details, applicability to text generation, and consistency to certain metrics which shed light on future directions.

Human evaluation in often considered to be the gold standard method of evaluating a Natural Language Generation system. However, whilst its importance is accepted by the community at large, the quality of its execution is often brought into question. In this position paper, we argue that the generation of more esoteric forms of language - humour, irony and sarcasm - constitutes a subdomain where the characteristics of selected evaluator panels are of utmost importance, and every effort should be made to report demographic characteristics wherever possible, in the interest of transparency and replicability. We support these claims with an overview of each language form and an analysis of examples in terms of how their interpretation is affected by different participant variables. We additionally perform a critical survey of recent works in NLG to assess how well evaluation procedures are reported in this subdomain, and note a severe lack of open reporting of evaluator demographic information, and a significant reliance on crowdsourcing platforms for recruitment.

Abstracts derived from biomedical literature possess distinct domain-specific characteristics, including specialised writing styles and biomedical terminologies, which necessitate a deep understanding of the related literature. As a result, existing language models struggle to generate technical summaries that are on par with those produced by biomedical experts, given the absence of domain-specific background knowledge. This paper aims to enhance the performance of language models in biomedical abstractive summarisation by aggregating knowledge from external papers cited within the source article. We propose a novel attention-based citation aggregation model that integrates domain-specific knowledge from citation papers, allowing neural networks to generate summaries by leveraging both the paper content and relevant knowledge from citation papers. Furthermore, we construct and release a large-scale biomedical summarisation dataset that serves as a foundation for our research. Extensive experiments demonstrate that our model outperforms state-of-the-art approaches and achieves substantial improvements in abstractive biomedical text summarisation.

In recent years, contrastive learning (CL) has been extensively utilized to recover sentence and document-level encoding capability from pre-trained language models. In this work, we question the length generalizability of CL-based models, i.e., their vulnerability towards length-induced semantic shift. We verify not only that length vulnerability is a significant yet overlooked research gap, but we can devise unsupervised CL methods solely depending on the semantic signal provided by document length. We first derive the theoretical foundations underlying length attacks, showing that elongating a document would intensify the high intra-document similarity that is already brought by CL. Moreover, we found that isotropy promised by CL is highly dependent on the length range of text exposed in training. Inspired by these findings, we introduce a simple yet universal document representation learning framework, **LA(SER)³**: length-agnostic self-reference for semantically robust sentence representation learning, achieving state-of-the-art unsupervised performance on the standard information retrieval benchmark. [Our code is publicly available.](https://github.com/gowitheflow-1998/LA-SER-cubed)

Many text mining models are constructed by fine-tuning a large deep pre-trained language model (PLM) in downstream tasks. However, a significant challenge that arises nowadays is how to maintain performance when we use a lightweight model with limited labeled samples. We present DisCo, a semi-supervised learning (SSL) framework for fine-tuning a cohort of small student models generated from a large PLM using knowledge distillation. Our key insight is to share complementary knowledge among distilled student cohorts to promote their SSL effectiveness. DisCo employs a novel co-training technique to optimize a cohort of multiple small student models by promoting knowledge sharing among students under diversified views: model views produced by different distillation strategies and data views produced by various input augmentations. We evaluate DisCo on both semi-supervised text classification and extractive summarization tasks. Experimental results show that DisCo can produce student models that are 7.6× smaller and 4.8 × faster in inference than the baseline PLMs while maintaining comparable performance. We also show that DisCo-generated student models outperform the similar-sized models elaborately tuned in distinct tasks.

Large language models (LLMs) achieved remarkable performance across various tasks. However, they face challenges in managing long documents and extended conversations, due to significantly increased computational requirements, both in memory and inference time, and potential context truncation when the input exceeds the LLM’s fixed context length. This paper proposes a method called Selective Context that enhances the inference efficiency of LLMs by identifying and pruning redundancy in the input context to make the input more compact. We test our approach using common data sources requiring long context processing: arXiv papers, news articles, and long conversations, on tasks of summarisation, question answering, and response generation. Experimental results show that Selective Context significantly reduces memory cost and decreases generation latency while maintaining comparable performance compared to that achieved when full context is used. Specifically, we achieve a 50% reduction in context cost, resulting in a 36% reduction in inference memory usage and a 32% reduction in inference time, while observing only a minor drop of .023 in BERTscore and .038 in faithfulness on four downstream applications, indicating that our method strikes a good balance between efficiency and performance.

Previous approaches for automatic lay summarisation are exclusively reliant on the source article that, given it is written for a technical audience (e.g., researchers), is unlikely to explicitly define all technical concepts or state all of the background information that is relevant for a lay audience. We address this issue by augmenting eLife, an existing biomedical lay summarisation dataset, with article-specific knowledge graphs, each containing detailed information on relevant biomedical concepts. Using both automatic and human evaluations, we systematically investigate the effectiveness of three different approaches for incorporating knowledge graphs within lay summarisation models, with each method targeting a distinct area of the encoder-decoder model architecture. Our results confirm that integrating graph-based domain knowledge can significantly benefit lay summarisation by substantially increasing the readability of generated text and improving the explanation of technical concepts.

We propose a novel RoBERTa-based model, RoPPT, which introduces a target-oriented parse tree structure in metaphor detection. Compared to existing models, RoPPT focuses on semantically relevant information and achieves the state-of-the-art on several main metaphor datasets. We also compare our approach against several popular denoising and pruning methods, demonstrating the effectiveness of our approach in context denoising. Our code and dataset can be found at https://github.com/MajiBear000/RoPPT.

In this paper, we propose FrameBERT, a BERT-based model that can explicitly learn and incorporate FrameNet Embeddings for concept-level metaphor detection. FrameBERT not only achieves better or comparable performance to the state-of-the-art, but also is more explainable and interpretable compared to existing models, attributing to its ability of accounting for external knowledge of FrameNet.

Natural Language Generation has been proved to be effective and efficient in constructing health behaviour change support systems. We are working on DrivingBeacon, a behaviour change support system that uses telematics data from mobile phone sensors to generate weekly data-to-text feedback reports to vehicle drivers. The system makes use of a wealth of information such as mobile phone use while driving, geo-information, speeding, rush hour driving to generate the feedback. We present results from a real-world evaluation where 8 drivers in UK used DrivingBeacon for 4 weeks. Results are promising but not conclusive.

Knowledge graph embedding methods are important for the knowledge graph completion (or link prediction) task.One state-of-the-art method, PairRE, leverages two separate vectors to model complex relations (i.e., 1-to-N, N-to-1, and N-to-N) in knowledge graphs. However, such a method strictly restricts entities on the hyper-ellipsoid surfaces which limits the optimization of entity distribution, leading to suboptimal performance of knowledge graph completion. To address this issue, we propose a novel score function TranSHER, which leverages relation-specific translations between head and tail entities to relax the constraint of hyper-ellipsoid restrictions. By introducing an intuitive and simple relation-specific translation, TranSHER can provide more direct guidance on optimization and capture more semantic characteristics of entities with complex relations. Experimental results show that TranSHER achieves state-of-the-art performance on link prediction and generalizes well to datasets in different domains and scales. Our codes are public available athttps://github.com/yizhilll/TranSHER.

Lay summarisation aims to jointly summarise and simplify a given text, thus making its content more comprehensible to non-experts.Automatic approaches for lay summarisation can provide significant value in broadening access to scientific literature, enabling a greater degree of both interdisciplinary knowledge sharing and public understanding when it comes to research findings. However, current corpora for this task are limited in their size and scope, hindering the development of broadly applicable data-driven approaches. Aiming to rectify these issues, we present two novel lay summarisation datasets, PLOS (large-scale) and eLife (medium-scale), each of which contains biomedical journal articles alongside expert-written lay summaries.We provide a thorough characterisation of our lay summaries, highlighting differing levels of readability and abstractivenessbetween datasets that can be leveraged to support the needs of different applications.Finally, we benchmark our datasets using mainstream summarisation approaches and perform a manual evaluation with domain experts, demonstrating their utility and casting light on the key challenges of this task.

Fairness has become a trending topic in natural language processing (NLP) and covers biases targeting certain social groups such as genders and religions. Yet regional bias, another long-standing global discrimination problem, remains unexplored still. Consequently, we intend to provide a study to analyse the regional bias learned by the pre-trained language models (LMs) that are broadly used in NLP tasks. While verifying the existence of regional bias in LMs, we find that the biases on regional groups can be largely affected by the corresponding geographical clustering. We accordingly propose a hierarchical regional bias evaluation method (HERB) utilising the information from the sub-region clusters to quantify the bias in the pre-trained LMs. Experiments show that our hierarchical metric can effectively evaluate the regional bias with regard to comprehensive topics and measure the potential regional bias that can be propagated to downstream tasks. Our codes are available at https://github.com/Bernard-Yang/HERB.

One of the key challenges of automatic story generation is how to generate a long narrative that can maintain fluency, relevance, and coherence. Despite recent progress, current story generation systems still face the challenge of how to effectively capture contextual and event features, which has a profound impact on a model’s generation performance. To address these challenges, we present EtriCA, a novel neural generation model, which improves the relevance and coherence of the generated stories through residually mapping context features to event sequences with a cross-attention mechanism. Such a feature capturing mechanism allows our model to better exploit the logical relatedness between events when generating stories. Extensive experiments based on both automatic and human evaluations show that our model significantly outperforms state-of-the-art baselines, demonstrating the effectiveness of our model in leveraging context and event features.

We present the development of a benchmark suite consisting of an annotation schema, training corpus and baseline model for Entity Recognition (ER) in job descriptions, published under a Creative Commons license. This was created to address the distinct lack of resources available to the community for the extraction of salient entities, such as skills, from job descriptions. The dataset contains 18.6k entities comprising five types (Skill, Qualification, Experience, Occupation, and Domain). We include a benchmark CRF-based ER model which achieves an F1 score of 0.59. Through the establishment of a standard definition of entities and training/testing corpus, the suite is designed as a foundation for future work on tasks such as the development of job recommender systems.

Story generation aims to generate a long narrative conditioned on a given input. In spite of the success of prior works with the application of pre-trained models, current neural models for Chinese stories still struggle to generate high-quality long text narratives. We hypothesise that this stems from ambiguity in syntactically parsing the Chinese language, which does not have explicit delimiters for word segmentation. Consequently, neural models suffer from the inefficient capturing of features in Chinese narratives. In this paper, we present a new generation framework that enhances the feature capturing mechanism by informing the generation model of dependencies between words and additionally augmenting the semantic representation learning through synonym denoising training. We conduct a range of experiments, and the results demonstrate that our framework outperforms the state-of-the-art Chinese generation models on all evaluation metrics, demonstrating the benefits of enhanced dependency and semantic representation learning.

To improve the performance of long text generation, recent studies have leveraged automatically planned event structures (i.e. storylines) to guide story generation. Such prior works mostly employ end-to-end neural generation models to predict event sequences for a story. However, such generation models struggle to guarantee the narrative coherence of separate events due to the hallucination problem, and additionally the generated event sequences are often hard to control due to the end-to-end nature of the models. To address these challenges, we propose NGEP, an novel event planning framework which generates an event sequence by performing inference on an automatically constructed event graph and enhances generalisation ability through a neural event advisor. We conduct a range of experiments on multiple criteria, and the results demonstrate that our graph-based neural framework outperforms the state-of-the-art (SOTA) event planning approaches, considering both the performance of event sequence generation and the effectiveness on the downstream task of story generation.

Metaphors are proven to have stronger emotional impact than literal expressions. Although this conclusion is shown to be promising in benefiting various NLP applications, the reasons behind this phenomenon are not well studied. This paper conducts the first study in exploring how metaphors convey stronger emotion than their literal counterparts. We find that metaphors are generally more specific than literal expressions. The more specific property of metaphor can be one of the reasons for metaphors’ superiority in emotion expression. When we compare metaphors with literal expressions with the same specificity level, the gap of emotion expressing ability between both reduces significantly. In addition, we observe specificity is crucial in literal language as well, as literal language can express stronger emotion by making it more specific.

Nominal metaphors are frequently used in human language and have been shown to be effective in persuading, expressing emotion, and stimulating interest. This paper tackles the problem of Chinese Nominal Metaphor (NM) generation. We introduce a novel multitask framework, which jointly optimizes three tasks: NM identification, NM component identification, and NM generation. The metaphor identification module is able to perform a self-training procedure, which discovers novel metaphors from a large-scale unlabeled corpus for NM generation. The NM component identification module emphasizes components during training and conditions the generation on these NM components for more coherent results. To train the NM identification and component identification modules, we construct an annotated corpus consisting of 6.3k sentences that contain diverse metaphorical patterns. Automatic metrics show that our method can produce diverse metaphors with good readability, where 92% of them are novel metaphorical comparisons. Human evaluation shows our model significantly outperforms baselines on consistency and creativity.

This paper explores the task of Difficulty-Controllable Question Generation (DCQG), which aims at generating questions with required difficulty levels. Previous research on this task mainly defines the difficulty of a question as whether it can be correctly answered by a Question Answering (QA) system, lacking interpretability and controllability. In our work, we redefine question difficulty as the number of inference steps required to answer it and argue that Question Generation (QG) systems should have stronger control over the logic of generated questions. To this end, we propose a novel framework that progressively increases question difficulty through step-by-step rewriting under the guidance of an extracted reasoning chain. A dataset is automatically constructed to facilitate the research, on which extensive experiments are conducted to test the performance of our method.

We present a fast and scalable architecture called Explicit Modular Decomposition (EMD), in which we incorporate both classification-based and extraction-based methods and design four modules (for clas- sification and sequence labelling) to jointly extract dialogue states. Experimental results based on the MultiWoz 2.0 dataset validates the superiority of our proposed model in terms of both complexity and scalability when compared to the state-of-the-art methods, especially in the scenario of multi-domain dialogues entangled with many turns of utterances.

Knowledge Graph Embeddings (KGEs) have been intensively explored in recent years due to their promise for a wide range of applications. However, existing studies focus on improving the final model performance without acknowledging the computational cost of the proposed approaches, in terms of execution time and environmental impact. This paper proposes a simple yet effective KGE framework which can reduce the training time and carbon footprint by orders of magnitudes compared with state-of-the-art approaches, while producing competitive performance. We highlight three technical innovations: full batch learning via relational matrices, closed-form Orthogonal Procrustes Analysis for KGEs, and non-negative-sampling training. In addition, as the first KGE method whose entity embeddings also store full relation information, our trained models encode rich semantics and are highly interpretable. Comprehensive experiments and ablation studies involving 13 strong baselines and two standard datasets verify the effectiveness and efficiency of our algorithm.

Cross-Lingual Word Embeddings (CLWEs) encode words from two or more languages in a shared high-dimensional space in which vectors representing words with similar meaning (regardless of language) are closely located. Existing methods for building high-quality CLWEs learn mappings that minimise the ℓ2 norm loss function. However, this optimisation objective has been demonstrated to be sensitive to outliers. Based on the more robust Manhattan norm (aka. ℓ1 norm) goodness-of-fit criterion, this paper proposes a simple post-processing step to improve CLWEs. An advantage of this approach is that it is fully agnostic to the training process of the original CLWEs and can therefore be applied widely. Extensive experiments are performed involving ten diverse languages and embeddings trained on different corpora. Evaluation results based on bilingual lexicon induction and cross-lingual transfer for natural language inference tasks show that the ℓ1 refinement substantially outperforms four state-of-the-art baselines in both supervised and unsupervised settings. It is therefore recommended that this strategy be adopted as a standard for CLWE methods.

We introduce the task of historical text summarisation, where documents in historical forms of a language are summarised in the corresponding modern language. This is a fundamentally important routine to historians and digital humanities researchers but has never been automated. We compile a high-quality gold-standard text summarisation dataset, which consists of historical German and Chinese news from hundreds of years ago summarised in modern German or Chinese. Based on cross-lingual transfer learning techniques, we propose a summarisation model that can be trained even with no cross-lingual (historical to modern) parallel data, and further benchmark it against state-of-the-art algorithms. We report automatic and human evaluations that distinguish the historic to modern language summarisation task from standard cross-lingual summarisation (i.e., modern to modern language), highlight the distinctness and value of our dataset, and demonstrate that our transfer learning approach outperforms standard cross-lingual benchmarks on this task.

Understanding speaker’s feelings and producing appropriate responses with emotion connection is a key communicative skill for empathetic dialogue systems. In this paper, we propose a simple technique called Affective Decoding for empathetic response generation. Our method can effectively incorporate emotion signals during each decoding step, and can additionally be augmented with an auxiliary dual emotion encoder, which learns separate embeddings for the speaker and listener given the emotion base of the dialogue. Extensive empirical studies show that our models are perceived to be more empathetic by human evaluations, in comparison to several strong mainstream methods for empathetic responding.

The Variational Autoencoder (VAE) is a popular and powerful model applied to text modelling to generate diverse sentences. However, an issue known as posterior collapse (or KL loss vanishing) happens when the VAE is used in text modelling, where the approximate posterior collapses to the prior, and the model will totally ignore the latent variables and be degraded to a plain language model during text generation. Such an issue is particularly prevalent when RNN-based VAE models are employed for text modelling. In this paper, we propose a simple, generic architecture called Timestep-Wise Regularisation VAE (TWR-VAE), which can effectively avoid posterior collapse and can be applied to any RNN-based VAE models. The effectiveness and versatility of our model are demonstrated in different tasks, including language modelling and dialogue response generation.

We propose DGST, a novel and simple Dual-Generator network architecture for text Style Transfer. Our model employs two generators only, and does not rely on any discriminators or parallel corpus for training. Both quantitative and qualitative experiments on the Yelp and IMDb datasets show that our model gives competitive performance compared to several strong baselines with more complicated architecture designs.

End-to-end training with Deep Neural Networks (DNN) is a currently popular method for metaphor identification. However, standard sequence tagging models do not explicitly take advantage of linguistic theories of metaphor identification. We experiment with two DNN models which are inspired by two human metaphor identification procedures. By testing on three public datasets, we find that our models achieve state-of-the-art performance in end-to-end metaphor identification.

Recognising dialogue acts (DA) is important for many natural language processing tasks such as dialogue generation and intention recognition. In this paper, we propose a dual-attention hierarchical recurrent neural network for DA classification. Our model is partially inspired by the observation that conversational utterances are normally associated with both a DA and a topic, where the former captures the social act and the latter describes the subject matter. However, such a dependency between DAs and topics has not been utilised by most existing systems for DA classification. With a novel dual task-specific attention mechanism, our model is able, for utterances, to capture information about both DAs and topics, as well as information about the interactions between them. Experimental results show that by modelling topic as an auxiliary task, our model can significantly improve DA classification, yielding better or comparable performance to the state-of-the-art method on three public datasets.

A prominent strand of work in formal semantics investigates the ways in which human languages quantify over the elements of a set, as when we say “All A are B”, “All except two A are B”, “Only a few of the A are B” and so on. Our aim is to build Natural Language Generation algorithms that mimic humans’ use of quantified expressions. To inform these algorithms, we conducted on a series of elicitation experiments in which human speakers were asked to perform a linguistic task that invites the use of quantified expressions. We discuss how these experiments were conducted and what corpora they gave rise to. We conduct an informal analysis of the corpora, and offer an initial assessment of the challenges that these corpora pose for Natural Language Generation. The dataset is available at: https://github.com/a-quei/qtuna.

Quantified expressions have always taken up a central position in formal theories of meaning and language use. Yet quantified expressions have so far attracted far less attention from the Natural Language Generation community than, for example, referring expressions. In an attempt to start redressing the balance, we investigate a recently developed corpus in which quantified expressions play a crucial role; the corpus is the result of a carefully controlled elicitation experiment, in which human participants were asked to describe visually presented scenes. Informed by an analysis of this corpus, we propose algorithms that produce computer-generated descriptions of a wider class of visual scenes, and we evaluate the descriptions generated by these algorithms in terms of their correctness, completeness, and human-likeness. We discuss what this exercise can teach us about the nature of quantification and about the challenges posed by the generation of quantified expressions.

Variational Autoencoder (VAE) is a powerful method for learning representations of high-dimensional data. However, VAEs can suffer from an issue known as latent variable collapse (or KL term vanishing), where the posterior collapses to the prior and the model will ignore the latent codes in generative tasks. Such an issue is particularly prevalent when employing VAE-RNN architectures for text modelling (Bowman et al., 2016; Yang et al., 2017). In this paper, we present a new architecture called Full-Sampling-VAE-RNN, which can effectively avoid latent variable collapse. Compared to the general VAE-RNN architectures, we show that our model can achieve much more stable training process and can generate text with significantly better quality.

Metaphoric expressions are widespread in natural language, posing a significant challenge for various natural language processing tasks such as Machine Translation. Current word embedding based metaphor identification models cannot identify the exact metaphorical words within a sentence. In this paper, we propose an unsupervised learning method that identifies and interprets metaphors at word-level without any preprocessing, outperforming strong baselines in the metaphor identification task. Our model extends to interpret the identified metaphors, paraphrasing them into their literal counterparts, so that they can be better translated by machines. We evaluated this with two popular translation systems for English to Chinese, showing that our model improved the systems significantly.

We introduce SimpleNLG-ZH, a realisation engine for Mandarin that follows the software design paradigm of SimpleNLG (Gatt and Reiter, 2009). We explain the core grammar (morphology and syntax) and the lexicon of SimpleNLG-ZH, which is very different from English and other languages for which SimpleNLG engines have been built. The system was evaluated by regenerating expressions from a body of test sentences and a corpus of human-authored expressions. Human evaluation was conducted to estimate the quality of regenerated sentences.

We extend the classic Referring Expressions Generation task by considering zero pronouns in “pro-drop” languages such as Chinese, modelling their use by means of the Bayesian Rational Speech Acts model (Frank and Goodman, 2012). By assuming that highly salient referents are most likely to be referred to by zero pronouns (i.e., pro-drop is more likely for salient referents than the less salient ones), the model offers an attractive explanation of a phenomenon not previously addressed probabilistically.

This paper argues that a new generic approach to statistical NLG can be made to perform Referring Expression Generation (REG) successfully. The model does not only select attributes and values for referring to a target referent, but also performs Linguistic Realisation, generating an actual Noun Phrase. Our evaluations suggest that the attribute selection aspect of the algorithm exceeds classic REG algorithms, while the Noun Phrases generated are as similar to those in a previously developed corpus as were Noun Phrases produced by a new set of human speakers.

This paper describes the system that we submitted for SemEval-2018 task 10: capturing discriminative attributes. Our system is built upon a simple idea of measuring the attribute word’s similarity with each of the two semantically similar words, based on an extended word embedding method and WordNet. Instead of computing the similarities between the attribute and semantically similar words by using standard word embeddings, we propose a novel method that combines word and context embeddings which can better measure similarities. Our model is simple and effective, which achieves an average F1 score of 0.62 on the test set.

Contrastive opinion mining is essential in identifying, extracting and organising opinions from user generated texts. Most existing studies separate input data into respective collections. In addition, the relationships between the topics extracted and the sentences in the corpus which express the topics are opaque, hindering our understanding of the opinions expressed in the corpus. We propose a novel unified latent variable model (contraLDA) which addresses the above matters. Experimental results show the effectiveness of our model in mining contrasted opinions, outperforming our baselines.

We develop a computational model to discover the potential causes of depression by analysing the topics in a usergenerated text. We show the most prominent causes, and how these causes evolve over time. Also, we highlight the differences in causes between students with low and high neuroticism. Our studies demonstrate that the topics reveal valuable clues about the causes contributing to depressed mood. Identifying causes can have a significant impact on improving the quality of depression care; thereby providing greater insights into a patient’s state for pertinent treatment recommendations. Hence, this study significantly expands the ability to discover the potential factors that trigger depression, making it possible to increase the efficiency of depression treatment.