Microblog content (e.g., Tweets) is noisy due to its informal use of language and its lack of contextual information within each post. To tackle these challenges, state-of-the-art microblog classification models rely on pre-training language models (LMs). However, pre-training dedicated LMs is resource-intensive and not suitable for small labs. Supervised contrastive learning (SCL) has shown its effectiveness with small, available resources. In this work, we examine the effectiveness of fine-tuning transformer-based language models, regularized with a SCL loss for English microblog classification. Despite its simplicity, the evaluation on two English microblog classification benchmarks (TweetEval and Tweet Topic Classification) shows an improvement over baseline models. The result shows that, across all subtasks, our proposed method has a performance gain of up to 11.9 percentage points. All our models are open source.

Following the introduction of the European Sustainability Reporting Standard (ESRS), companies will have to adapt to a new policy and provide mandatory sustainability reports. However, implementing such reports entails a challenge, such as the comprehension of a large number of textual information from various sources. This task can be accelerated by employing Large Language Models (LLMs) and ontologies to effectively model the domain knowledge. In this study, we extended an existing ontology to model ESRS Topical Standard for disclosure. The developed ontology would enable automated reasoning over the data and assist in constructing Knowledge Graphs (KGs). Moreover, the proposed ontology extension would also help to identify gaps in companies’ sustainability reports with regard to the ESRS requirements.Additionally, we extracted knowledge from corporate sustainability reports via LLMs guided with a proposed ontology and developed their KG representation.

Identifying events from text has a long past in narrative analysis, but a short history in Natural Language Processing (NLP). In this position paper, a question is asked: given the telling of a sequence of real-world events by a news narrator, what do NLP event extraction models capture, and what do they miss? Insights from critical discourse analysis (CDA) and from a series of movements in literary criticism motivate us to model the narrated logic in news narratives.As a result, a computational framework is proposed to model the function of news narration, which shapes the narrated world, consumed by news narratees. As a simplification, we represent the causal logic between events depicted in the narrated world.

This paper describes the results of the Knowledge Graph Question Answering (KGQA) shared task that was co-located with the TextGraphs 2024 workshop. In this task, given a textual question and a list of entities with the corresponding KG subgraphs, the participating system should choose the entity that correctly answers the question. Our competition attracted thirty teams, four of which outperformed our strong ChatGPT-based zero-shot baseline. In this paper, we overview the participating systems and analyze their performance according to a large-scale automatic evaluation. To the best of our knowledge, this is the first competition aimed at the KGQA problem using the interaction between large language models (LLMs) and knowledge graphs.

In the realm of Machine Learning and Deep Learning, there is a need for high-quality annotated data to train and evaluate supervised models. An extensive number of annotation tools have been developed to facilitate the data labelling process. However, finding the right tool is a demanding task involving thorough searching and testing. Hence, to effectively navigate the multitude of tools, it becomes essential to ensure their findability, accessibility, interoperability, and reusability (FAIR). This survey addresses the FAIRness of existing annotation software by evaluating 50 different tools against the FAIR principles for research software (FAIR4RS). The study indicates that while being accessible and interoperable, annotation tools are difficult to find and reuse. In addition, there is a need to establish community standards for annotation software development, documentation, and distribution.

Question Answering (QA) systems return concise answers or answer lists based on natural language text, which uses a given context document. Many resources go into curating QA datasets to advance the development of robust QA models. There is a surge in QA datasets for languages such as English; this is different for low-resource languages like Amharic. Indeed, there is no published or publicly available Amharic QA dataset. Hence, to foster further research in low-resource QA, we present the first publicly available benchmarking Amharic Question Answering Dataset (Amh-QuAD). We crowdsource 2,628 question-answer pairs from over 378 Amharic Wikipedia articles. Using the training set, we fine-tune an XLM-R-based language model and introduce a new reader model. Leveraging our newly fine-tuned reader run a baseline model to spark open-domain Amharic QA research interest. The best- performing baseline QA achieves an F-score of 80.3 and 81.34 in retriever-reader and reading comprehension settings.

In this work, we analyse the role of output vocabulary for text-to-text (T2T) models on the task of SPARQL semantic parsing. We perform experiments within the the context of knowledge graph question answering (KGQA), where the task is to convert questions in natural language to the SPARQL query language. We observe that the query vocabulary is distinct from human vocabulary. Language Models (LMs) are pre-dominantly trained for human language tasks, and hence, if the query vocabulary is replaced with a vocabulary more attuned to the LM tokenizer, the performance of models may improve. We carry out carefully selected vocabulary substitutions on the queries and find absolute gains in the range of 17% on the GrailQA dataset.

Evaluating Natural Language Generation (NLG) systems is a challenging task. Firstly, the metric should ensure that the generated hypothesis reflects the reference’s semantics. Secondly, it should consider the grammatical quality of the generated sentence. Thirdly, it should be robust enough to handle various surface forms of the generated sentence. Thus, an effective evaluation metric has to be multifaceted. In this paper, we propose an automatic evaluation metric incorporating several core aspects of natural language understanding (language competence, syntactic and semantic variation). Our proposed metric, RoMe, is trained on language features such as semantic similarity combined with tree edit distance and grammatical acceptability, using a self-supervised neural network to assess the overall quality of the generated sentence. Moreover, we perform an extensive robustness analysis of the state-of-the-art methods and RoMe. Empirical results suggest that RoMe has a stronger correlation to human judgment over state-of-the-art metrics in evaluating system-generated sentences across several NLG tasks.

Task-oriented dialogue generation is challenging since the underlying knowledge is often dynamic and effectively incorporating knowledge into the learning process is hard. It is particularly challenging to generate both human-like and informative responses in this setting. Recent research primarily focused on various knowledge distillation methods where the underlying relationship between the facts in a knowledge base is not effectively captured. In this paper, we go one step further and demonstrate how the structural information of a knowledge graph can improve the system’s inference capabilities. Specifically, we propose DialoKG, a novel task-oriented dialogue system that effectively incorporates knowledge into a language model. Our proposed system views relational knowledge as a knowledge graph and introduces (1) a structure-aware knowledge embedding technique, and (2) a knowledge graph-weighted attention masking strategy to facilitate the system selecting relevant information during the dialogue generation. An empirical evaluation demonstrates the effectiveness of DialoKG over state-of-the-art methods on several standard benchmark datasets.

Data-driven systems need to be evaluated to establish trust in the scientific approach and its applicability. In particular, this is true for Knowledge Graph (KG) Question Answering (QA), where complex data structures are made accessible via natural-language interfaces. Evaluating the capabilities of these systems has been a driver for the community for more than ten years while establishing different KGQA benchmark datasets. However, comparing different approaches is cumbersome. The lack of existing and curated leaderboards leads to a missing global view over the research field and could inject mistrust into the results. In particular, the latest and most-used datasets in the KGQA community, LC-QuAD and QALD, miss providing central and up-to-date points of trust. In this paper, we survey and analyze a wide range of evaluation results with significant coverage of 100 publications and 98 systems from the last decade. We provide a new central and open leaderboard for any KGQA benchmark dataset as a focal point for the community - https://kgqa.github.io/leaderboard/. Our analysis highlights existing problems during the evaluation of KGQA systems. Thus, we will point to possible improvements for future evaluations.

Knowledge graphs are increasingly used in a plethora of downstream tasks or in the augmentation of statistical models to improve factuality. However, social biases are engraved in these representations and propagate downstream. We conducted a critical analysis of literature concerning biases at different steps of a knowledge graph lifecycle. We investigated factors introducing bias, as well as the biases that are rendered by knowledge graphs and their embedded versions afterward. Limitations of existing measurement and mitigation strategies are discussed and paths forward are proposed.

The automatic evaluation of open-domain dialogues remains a largely unsolved challenge. Despite the abundance of work done in the field, human judges have to evaluate dialogues’ quality. As a consequence, performing such evaluations at scale is usually expensive. This work investigates using a deep-learning model trained on the General Language Understanding Evaluation (GLUE) benchmark to serve as a quality indication of open-domain dialogues. The aim is to use the various GLUE tasks as different perspectives on judging the quality of conversation, thus reducing the need for additional training data or responses that serve as quality references. Due to this nature, the method can infer various quality metrics and can derive a component-based overall score. We achieve statistically significant correlation coefficients of up to 0.7.

Computer-based systems for communication with humans are a cornerstone of AI research since the 1950s. So far, the most effective way to assess the quality of the dialogues produced by these systems is to use resource-intensive manual labor instead of automated means. In this work, we investigate whether language models (LM) based on transformer neural networks can indicate the quality of a conversation. In a general sense, language models are methods that learn to predict one or more words based on an already given context. Due to their unsupervised nature, they are candidates for efficient, automatic indication of dialogue quality. We demonstrate that human evaluators have a positive correlation between the output of the language models and scores. We also provide some insights into their behavior and inner-working in a conversational context.

Dialogue systems for interaction with humans have been enjoying increased popularity in the research and industry fields. To this day, the best way to estimate their success is through means of human evaluation and not automated approaches, despite the abundance of work done in the field. In this paper, we investigate the effectiveness of perceiving dialogue evaluation as an anomaly detection task. The paper looks into four dialogue modeling approaches and how their objective functions correlate with human annotation scores. A high-level perspective exhibits negative results. However, a more in-depth look shows some potential for using anomaly detection for evaluating dialogues.

Hyper-relational knowledge graphs (KGs) (e.g., Wikidata) enable associating additional key-value pairs along with the main triple to disambiguate, or restrict the validity of a fact. In this work, we propose a message passing based graph encoder - StarE capable of modeling such hyper-relational KGs. Unlike existing approaches, StarE can encode an arbitrary number of additional information (qualifiers) along with the main triple while keeping the semantic roles of qualifiers and triples intact. We also demonstrate that existing benchmarks for evaluating link prediction (LP) performance on hyper-relational KGs suffer from fundamental flaws and thus develop a new Wikidata-based dataset - WD50K. Our experiments demonstrate that StarE based LP model outperforms existing approaches across multiple benchmarks. We also confirm that leveraging qualifiers is vital for link prediction with gains up to 25 MRR points compared to triple-based representations.

With regard to the wider area of AI/LT platform interoperability, we concentrate on two core aspects: (1) cross-platform search and discovery of resources and services; (2) composition of cross-platform service workflows. We devise five different levels (of increasing complexity) of platform interoperability that we suggest to implement in a wider federation of AI/LT platforms. We illustrate the approach using the five emerging AI/LT platforms AI4EU, ELG, Lynx, QURATOR and SPEAKER.

The manual creation of gold standards for named entity recognition and entity linking is time- and resource-intensive. Moreover, recent works show that such gold standards contain a large proportion of mistakes in addition to being difficult to maintain. We hence present Bengal, a novel automatic generation of such gold standards as a complement to manually created benchmarks. The main advantage of our benchmarks is that they can be readily generated at any time. They are also cost-effective while being guaranteed to be free of annotation errors. We compare the performance of 11 tools on benchmarks in English generated by Bengal and on 16 benchmarks created manually. We show that our approach can be ported easily across languages by presenting results achieved by 4 tools on both Brazilian Portuguese and Spanish. Overall, our results suggest that our automatic benchmark generation approach can create varied benchmarks that have characteristics similar to those of existing benchmarks. Our approach is open-source. Our experimental results are available at http://faturl.com/bengalexpinlg and the code at https://github.com/dice-group/BENGAL.

In the last couple of years the amount of structured open government data has increased significantly. Already now, citizens are able to leverage the advantages of open data through increased transparency and better opportunities to take part in governmental decision making processes. Our approach increases the interoperability of existing but distributed open governmental datasets by converting them to the RDF-based NLP Interchange Format (NIF). Furthermore, we integrate the converted data into a geodata store and present a user interface for querying this data via a keyword-based search. The language resource generated in this project is publicly available for download and also via a dedicated SPARQL endpoint.

Extracting Linked Data following the Semantic Web principle from unstructured sources has become a key challenge for scientific research. Named Entity Recognition and Disambiguation are two basic operations in this extraction process. One step towards the realization of the Semantic Web vision and the development of highly accurate tools is the availability of data for validating the quality of processes for Named Entity Recognition and Disambiguation as well as for algorithm tuning. This article presents three novel, manually curated and annotated corpora (N3). All of them are based on a free license and stored in the NLP Interchange Format to leverage the Linked Data character of our datasets.