Automatic evaluation approaches (ROUGE, BERTScore, LLM-based evaluators) have been widely used to evaluate summarization tasks. Despite the complexities of script differences and tokenization, these approaches have been indiscriminately applied to summarization across multiple languages. While previous works have argued that these approaches correlate strongly with human ratings in English, it remains unclear whether the conclusion holds for other languages. To answer this question, we construct a small-scale pilot dataset containing article-summary pairs and human ratings in English, Chinese and Indonesian. To measure the strength of summaries, our ratings are measured as head-to-head comparisons with resulting Elo scores across four dimensions. Our analysis reveals that standard metrics are unreliable measures of quality, and that these problems are exacerbated in Chinese and Indonesian. We advocate for more nuanced and careful considerations in designing a robust evaluation framework for multiple languages.

Text simplification is the process of rewriting a piece of text using simpler vocabulary and grammatical structure in order to make the text more accessible and understandable for a larger audience. In this paper, we introduce a new text simplification model based on the notion of adaptive teaching using a teacher network and a text generation network. We name this new model Simplification via Adaptive Teaching (SAT). Our proposed model sets a new state-of-the-art performance in terms of standard simplification metrics such as SARI and D-SARI with a significant improvement over the previous state of the art on the D-Wikipedia dataset and the Wiki-Doc benchmark dataset. Moreover, we conduct a human evaluation in terms of text simplicity, correctness, and fluency to substantiate SAT’s performance.

A primary criticism towards language models (LMs) is their inscrutability. This paper presents evidence that, despite their size and complexity, LMs sometimes exploit a simple vector arithmetic style mechanism to solve some relational tasks using regularities encoded in the hidden space of the model (e.g., Poland:Warsaw::China:Beijing). We investigate a range of language model sizes (from 124M parameters to 176B parameters) in an in-context learning setting, and find that for a variety of tasks (involving capital cities, uppercasing, and past-tensing) a key part of the mechanism reduces to a simple additive update typically applied by the feedforward (FFN) networks. We further show that this mechanism is specific to tasks that require retrieval from pretraining memory, rather than retrieval from local context. Our results contribute to a growing body of work on the interpretability of LMs, and offer reason to be optimistic that, despite the massive and non-linear nature of the models, the strategies they ultimately use to solve tasks can sometimes reduce to familiar and even intuitive algorithms.

Cross-lingual summarization (CLS) has attracted increasing interest in recent years due to the availability of large-scale web-mined datasets and the advancements of multilingual language models. However, given the rareness of naturally occurring CLS resources, the majority of datasets are forced to rely on translation which can contain overly literal artifacts. This restricts our ability to observe naturally occurring CLS pairs that capture organic diction, including instances of code-switching. This alteration between languages in mid-message is a common phenomenon in multilingual settings yet has been largely overlooked in cross-lingual contexts due to data scarcity. To address this gap, we introduce CroCoSum, a dataset of cross-lingual code-switched summarization of technology news. It consists of over 24,000 English source articles and 18,000 human-written Chinese news summaries, with more than 92% of the summaries containing code-switched phrases. For reference, we evaluate the performance of existing approaches including pipeline, end-to-end, and zero-shot methods. We show that leveraging existing CLS resources as a pretraining step does not improve performance on CroCoSum, indicating the limited generalizability of current datasets. Finally, we discuss the challenges of evaluating cross-lingual summarizers on code-switched generation through qualitative error analyses.

Document-level text simplification is a specific type of simplification which involves simplifying documents consisting of several sentences by rewriting them into fewer or more sentences. In this paper, we propose a new two-stage framework SIMSUM for automated document-level text simplification. Our model is designed with explicit summarization and simplification models and guides the generation using the main keywords of a source text. In order to evaluate our new model, we use two existing benchmark datasets for simplification, namely D-Wikipedia and Wiki-Doc. We compare our model’s performance with state of the art and show that SIMSUM achieves top results on the D-Wikipedia dataset SARI (+1.20), D-SARI (+1.64), and FKGL (-0.35) scores, improving over the best baseline models. In order to evaluate the quality of the generated text, we analyze the outputs from different models qualitatively and demonstrate the merit of our new model. Our code and datasets are available.

Sparse annotation poses persistent challenges to training dense retrieval models; for example, it distorts the training signal when unlabeled relevant documents are used spuriously as negatives in contrastive learning. To alleviate this problem, we introduce evidence-based label smoothing, a novel, computationally efficient method that prevents penalizing the model for assigning high relevance to false negatives. To compute the target relevance distribution over candidate documents within the ranking context of a given query, we assign a non-zero relevance probability to those candidates most similar to the ground truth based on the degree of their similarity to the ground-truth document(s). To estimate relevance we leverage an improved similarity metric based on reciprocal nearest neighbors, which can also be used independently to rerank candidates in post-processing. Through extensive experiments on two large-scale ad hoc text retrieval datasets, we demonstrate that reciprocal nearest neighbors can improve the ranking effectiveness of dense retrieval models, both when used for label smoothing, as well as for reranking. This indicates that by considering relationships between documents and queries beyond simple geometric distance we can effectively enhance the ranking context.

Representations from large language models (LLMs) are known to be dominated by a small subset of dimensions with exceedingly high variance. Previous works have argued that although ablating these outlier dimensions in LLM representations hurts downstream performance, outlier dimensions are detrimental to the representational quality of embeddings. In this study, we investigate how fine-tuning impacts outlier dimensions and show that 1) outlier dimensions that occur in pre-training persist in fine-tuned models and 2) a single outlier dimension can complete downstream tasks with a minimal error rate. Our results suggest that outlier dimensions can encode crucial task-specific knowledge and that the value of a representation in a single outlier dimension drives downstream model decisions.

Large pre-trained language models contain societal biases and carry along these biases to downstream tasks. Current in-processing bias mitigation approaches (like adversarial training) impose debiasing by updating a model’s parameters, effectively transferring the model to a new, irreversible debiased state. In this work, we propose a novel approach to develop stand-alone debiasing functionalities separate from the model, which can be integrated into the model on-demand, while keeping the core model untouched. Drawing from the concept of AdapterFusion in multi-task learning, we introduce DAM (Debiasing with Adapter Modules) – a debiasing approach to first encapsulate arbitrary bias mitigation functionalities into separate adapters, and then add them to the model on-demand in order to deliver fairness qualities. We conduct a large set of experiments on three classification tasks with gender, race, and age as protected attributes. Our results show that DAM improves or maintains the effectiveness of bias mitigation, avoids catastrophic forgetting in a multi-attribute scenario, and maintains on-par task performance, while granting parameter-efficiency and easy switching between the original and debiased models.

In recent years, large-scale transformer decoders such as the GPT-x family of models have become increasingly popular. Studies examining the behavior of these models tend to focus only on the output of the language modeling head and avoid analysis of the internal states of the transformer decoder. In this study, we present a collection of methods to analyze the hidden states of GPT-2 and use the model’s navigation of garden path sentences as a case study. To enable this, we compile the largest currently available dataset of garden path sentences. We show that Manhattan distances and cosine similarities provide more reliable insights compared to established surprisal methods that analyze next-token probabilities computed by a language modeling head. Using these methods, we find that negating tokens have minimal impacts on the model’s representations for unambiguous forms of sentences with ambiguity solely over what the object of a verb is, but have a more substantial impact of representations for unambiguous sentences whose ambiguity would stem from the voice of a verb. Further, we find that analyzing the decoder model’s hidden states reveals periods of ambiguity that might conclude in a garden path effect but happen not to, whereas surprisal analyses routinely miss this detail.

Contrastive learning has been the dominant approach to training dense retrieval models. In this work, we investigate the impact of ranking context - an often overlooked aspect of learning dense retrieval models. In particular, we examine the effect of its constituent parts: jointly scoring a large number of negatives per query, using retrieved (query-specific) instead of random negatives, and a fully list-wise loss.To incorporate these factors into training, we introduce Contextual Document Embedding Reranking (CODER), a highly efficient retrieval framework. When reranking, it incurs only a negligible computational overhead on top of a first-stage method at run time (approx. 5 ms delay per query), allowing it to be easily combined with any state-of-the-art dual encoder method. Models trained through CODER can also be used as stand-alone retrievers.Evaluating CODER in a large set of experiments on the MS MARCO and TripClick collections, we show that the contextual reranking of precomputed document embeddings leads to a significant improvement in retrieval performance. This improvement becomes even more pronounced when more relevance information per query is available, shown in the TripClick collection, where we establish new state-of-the-art results by a large margin.

Text summarization models are approaching human levels of fidelity. Existing benchmarking corpora provide concordant pairs of full and abridged versions of Web, news or professional content. To date, all summarization datasets operate under a one-size-fits-all paradigm that may not reflect the full range of organic summarization needs. Several recently proposed models (e.g., plug and play language models) have the capacity to condition the generated summaries on a desired range of themes. These capacities remain largely unused and unevaluated as there is no dedicated dataset that would support the task of topic-focused summarization. This paper introduces the first topical summarization corpus NEWTS, based on the well-known CNN/Dailymail dataset, and annotated via online crowd-sourcing. Each source article is paired with two reference summaries, each focusing on a different theme of the source document. We evaluate a representative range of existing techniques and analyze the effectiveness of different prompting methods.

The recent success of distributed word representations has led to an increased interest in analyzing the properties of their spatial distribution. Several studies have suggested that contextualized word embedding models do not isotropically project tokens into vector space. However, current methods designed to measure isotropy, such as average random cosine similarity and the partition score, have not been thoroughly analyzed and are not appropriate for measuring isotropy. We propose IsoScore: a novel tool that quantifies the degree to which a point cloud uniformly utilizes the ambient vector space. Using rigorously designed tests, we demonstrate that IsoScore is the only tool available in the literature that accurately measures how uniformly distributed variance is across dimensions in vector space. Additionally, we use IsoScore to challenge a number of recent conclusions in the NLP literature that have been derived using brittle metrics of isotropy. We caution future studies from using existing tools to measure isotropy in contextualized embedding space as resulting conclusions will be misleading or altogether inaccurate.

Lexical semantics and cognitive science point to affordances (i.e. the actions that objects support) as critical for understanding and representing nouns and verbs. However, study of these semantic features has not yet been integrated with the ?foundation? models that currently dominate language representation research. We hypothesize that predictive modeling of object state over time will result in representations that encode object affordance information ?for free?. We train a neural network to predict objects? trajectories in a simulated interaction and show that our network?s latent representations differentiate between both observed and unobserved affordances. We find that models trained using 3D simulations outperform conventional 2D computer vision models trained on a similar task, and, on initial inspection, that differences between concepts correspond to expected features (e.g., roll entails rotation) . Our results suggest a way in which modern deep learning approaches to grounded language learning can be integrated with traditional formal semantic notions of lexical representations.

In the pursuit of natural language understanding, there has been a long standing interest in tracking state changes throughout narratives. Impressive progress has been made in modeling the state of transaction-centric dialogues and procedural texts. However, this problem has been less intensively studied in the realm of general discourse where ground truth descriptions of states may be loosely defined and state changes are less densely distributed over utterances. This paper proposes to turn to simplified, fully observable systems that show some of these properties: Sports events. We curated 2,263 soccer matches including time-stamped natural language commentary accompanied by discrete events such as a team scoring goals, switching players or being penalized with cards. We propose a new task formulation where, given paragraphs of commentary of a game at different timestamps, the system is asked to recognize the occurrence of in-game events. This domain allows for rich descriptions of state while avoiding the complexities of many other real-world settings. As an initial point of performance measurement, we include two baseline methods from the perspectives of sentence classification with temporal dependence and current state-of-the-art generative model, respectively, and demonstrate that even sophisticated existing methods struggle on the state tracking task when the definition of state broadens or non-event chatter becomes prevalent.

Topic models are useful tools for analyzing and interpreting the main underlying themes of large corpora of text. Most topic models rely on word co-occurrence for computing a topic, i.e., a weighted set of words that together represent a high-level semantic concept. In this paper, we propose a new light-weight Self-Supervised Neural Topic Model (SNTM) that learns a rich context by learning a topic representation jointly from three co-occurring words and a document that the triple originates from. Our experimental results indicate that our proposed neural topic model, SNTM, outperforms previously existing topic models in coherence metrics as well as document clustering accuracy. Moreover, apart from the topic coherence and clustering performance, the proposed neural topic model has a number of advantages, namely, being computationally efficient and easy to train.

In politics, neologisms are frequently invented for partisan objectives. For example, “undocumented workers” and “illegal aliens” refer to the same group of people (i.e., they have the same denotation), but they carry clearly different connotations. Examples like these have traditionally posed a challenge to reference-based semantic theories and led to increasing acceptance of alternative theories (e.g., Two-Factor Semantics) among philosophers and cognitive scientists. In NLP, however, popular pretrained models encode both denotation and connotation as one entangled representation. In this study, we propose an adversarial nerual netowrk that decomposes a pretrained representation as independent denotation and connotation representations. For intrinsic interpretability, we show that words with the same denotation but different connotations (e.g., “immigrants” vs. “aliens”, “estate tax” vs. “death tax”) move closer to each other in denotation space while moving further apart in connotation space. For extrinsic application, we train an information retrieval system with our disentangled representations and show that the denotation vectors improve the viewpoint diversity of document rankings.

Virtual Worlds (VW) are online environments where people come together to interact and perform various tasks. The chat transcripts of interactions in VWs pose unique opportunities and challenges for language analysis: Firstly, the language of the transcripts is very brief, informal, and task-oriented. Secondly, in addition to chat, a VW system records users' in-world activities. Such a record could allow us to analyze how the language of interactions is linked to the users actions. For example, we can make the language analysis of the users dialogues more effective by taking into account the context of the corresponding action or we can predict or detect users actions by analyzing the content of conversations. Thirdly, a joined analysis of both the language and the actions would empower us to build effective modes of the users and their behavior. In this paper we present a corpus constructed from logs from an online multiplayer game BladeMistress. We describe the original logs, annotations that we created on the data, and summarize some of the experiments.