Riza Batista-Navarro

Hao Li, Yuping Wu, Viktor Schlegel et al. · tencent-ai

Medical progress notes play a crucial role in documenting a patient's hospital journey, including his or her condition, treatment plan, and any updates for healthcare providers. Automatic summarisation of a patient's problems in the form of a problem list can aid stakeholders in understanding a patient's condition, reducing workload and cognitive bias. BioNLP 2023 Shared Task 1A focuses on generating a list of diagnoses and problems from the provider's progress notes during hospitalisation. In this paper, we introduce our proposed approach to this task, which integrates two complementary components. One component employs large language models (LLMs) for data augmentation; the other is an abstractive summarisation LLM with a novel pre-training objective for generating the patients' problems summarised as a list. Our approach was ranked second among all submissions to the shared task. The performance of our model on the development and test datasets shows that our approach is more robust on unknown data, with an improvement of up to 3.1 points over the same size of the larger model.

Erick Mendez Guzman, Viktor Schlegel, Riza Batista-Navarro

Forced labour is the most common type of modern slavery, and it is increasingly gaining the attention of the research and social community. Recent studies suggest that artificial intelligence (AI) holds immense potential for augmenting anti-slavery action. However, AI tools need to be developed transparently in cooperation with different stakeholders. Such tools are contingent on the availability and access to domain-specific data, which are scarce due to the near-invisible nature of forced labour. To the best of our knowledge, this paper presents the first openly accessible English corpus annotated for multi-class and multi-label forced labour detection. The corpus consists of 989 news articles retrieved from specialised data sources and annotated according to risk indicators defined by the International Labour Organization (ILO). Each news article was annotated for two aspects: (1) indicators of forced labour as classification labels and (2) snippets of the text that justify labelling decisions. We hope that our data set can help promote research on explainability for multi-class and multi-label text classification. In this work, we explain our process for collecting the data underpinning the proposed corpus, describe our annotation guidelines and present some statistical analysis of its content. Finally, we summarise the results of baseline experiments based on different variants of the Bidirectional Encoder Representation from Transformer (BERT) model.

Sarah Alsayyahi, Riza Batista-Navarro

Temporal relation extraction models have thus far been hindered by a number of issues in existing temporal relation-annotated news datasets, including: (1) low inter-annotator agreement due to the lack of specificity of their annotation guidelines in terms of what counts as a temporal relation; (2) the exclusion of long-distance relations within a given document (those spanning across different paragraphs); and (3) the exclusion of events that are not centred on verbs. This paper aims to alleviate these issues by presenting a new annotation scheme that clearly defines the criteria based on which temporal relations should be annotated. Additionally, the scheme includes events even if they are not expressed as verbs (e.g., nominalised events). Furthermore, we propose a method for annotating all temporal relations -- including long-distance ones -- which automates the process, hence reducing time and manual effort on the part of annotators. The result is a new dataset, the TIMELINE corpus, in which improved inter-annotator agreement was obtained, in comparison with previously reported temporal relation datasets. We report the results of training and evaluating baseline temporal relation extraction models on the new corpus, and compare them with results obtained on the widely used MATRES corpus.

Viktor Schlegel, Erick Mendez-Guzman, Riza Batista-Navarro

Progress on many Natural Language Processing (NLP) tasks, such as text classification, is driven by objective, reproducible and scalable evaluation via publicly available benchmarks. However, these are not always representative of real-world scenarios where text classifiers are employed, such as sentiment analysis or misinformation detection. In this position paper, we put forward two points that aim to alleviate this problem. First, we propose to extend text classification benchmarks to evaluate the explainability of text classifiers. We review challenges associated with objectively evaluating the capabilities to produce valid explanations which leads us to the second main point: We propose to ground these benchmarks in human-centred applications, for example by using social media, gamification or to learn explainability metrics from human judgements.

Muhammad Arshad Khan, Max Kenney, Jack Painter et al.

In this paper, we present a grammar-based natural language framework for robot programming, specifically for pick-and-place tasks. Our approach uses a custom dictionary of action words, designed to store together words that share meaning, allowing for easy expansion of the vocabulary by adding more action words from a lexical database. We validate our Natural Language Robot Programming (NLRP) framework through simulation and real-world experimentation, using a Franka Panda robotic arm equipped with a calibrated camera-in-hand and a microphone. Participants were asked to complete a pick-and-place task using verbal commands, which were converted into text using Google's Speech-to-Text API and processed through the NLRP framework to obtain joint space trajectories for the robot. Our results indicate that our approach has a high system usability score. The framework's dictionary can be easily extended without relying on transfer learning or large data sets. In the future, we plan to compare the presented framework with different approaches of human-assisted pick-and-place tasks via a comprehensive user study.

Haifa Alrdahi, Riza Batista-Navarro

Learning chess strategies has been investigated widely, with most studies focussing on learning from previous games using search algorithms. Chess textbooks encapsulate grandmaster knowledge, explain playing strategies and require a smaller search space compared to traditional chess agents. This paper examines chess textbooks as a new knowledge source for enabling machines to learn how to play chess -- a resource that has not been explored previously. We developed the LEAP corpus, a first and new heterogeneous dataset with structured (chess move notations and board states) and unstructured data (textual descriptions) collected from a chess textbook containing 1164 sentences discussing strategic moves from 91 games. We firstly labelled the sentences based on their relevance, i.e., whether they are discussing a move. Each relevant sentence was then labelled according to its sentiment towards the described move. We performed empirical experiments that assess the performance of various transformer-based baseline models for sentiment analysis. Our results demonstrate the feasibility of employing transformer-based sentiment analysis models for evaluating chess moves, with the best performing model obtaining a weighted micro F_1 score of 68%. Finally, we synthesised the LEAP corpus to create a larger dataset, which can be used as a solution to the limited textual resource in the chess domain.

Filippos Ventirozos, Sarah Clinch, Riza Batista-Navarro

Semantic parsing of user-generated instructional text, in the way of enabling end-users to program the Internet of Things (IoT), is an underexplored area. In this study, we provide a unique annotated corpus which aims to support the transformation of cooking recipe instructions to machine-understandable commands for IoT devices in the kitchen. Each of these commands is a tuple capturing the semantics of an instruction involving a kitchen device in terms of "What", "Where", "Why" and "How". Based on this corpus, we developed machine learning-based sequence labelling methods, namely conditional random fields (CRF) and a neural network model, in order to parse recipe instructions and extract our tuples of interest from them. Our results show that while it is feasible to train semantic parsers based on our annotations, most natural-language instructions are incomplete, and thus transforming them into formal meaning representation, is not straightforward.

Viktor Schlegel, Goran Nenadic, Riza Batista-Navarro

Performance of NLP systems is typically evaluated by collecting a large-scale dataset by means of crowd-sourcing to train a data-driven model and evaluate it on a held-out portion of the data. This approach has been shown to suffer from spurious correlations and the lack of challenging examples that represent the diversity of natural language. Instead, we examine a framework for evaluating optimised models in training-set free setting on synthetically generated challenge sets. We find that despite the simplicity of the generation method, the data can compete with crowd-sourced datasets with regard to naturalness and lexical diversity for the purpose of evaluating the linguistic capabilities of MRC models. We conduct further experiments and show that state-of-the-art language model-based MRC systems can learn to succeed on the challenge set correctly, although, without capturing the general notion of the evaluated phenomenon.

Siwei Wu, Yizhi Li, Xingwei Qu et al.

Large Language Models (LLMs) have achieved remarkable success in various natural language processing tasks, yet their ability to generate long-form content remains poorly understood and evaluated. Our analysis reveals that current LLMs struggle with length requirements and information density in long-text generation, with performance deteriorating as text length increases. To quantitively locate such a performance degradation and provide further insights on model development, we present LongEval, a benchmark that evaluates long-text generation through both direct and plan-based generation paradigms, inspired by cognitive and linguistic writing models. The comprehensive experiments in this work reveal interesting findings such as that while model size correlates with generation ability, the small-scale model (e.g., LongWriter), well-trained on long texts, has comparable performance. All code and datasets are released in https://github.com/Wusiwei0410/LongEval.

Kung Yin Hong, Lifeng Han, Riza Batista-Navarro et al.

Neural Machine Translation (NMT) for low-resource languages is still a challenging task in front of NLP researchers. In this work, we deploy a standard data augmentation methodology by back-translation to a new language translation direction Cantonese-to-English. We present the models we fine-tuned using the limited amount of real data and the synthetic data we generated using back-translation including OpusMT, NLLB, and mBART. We carried out automatic evaluation using a range of different metrics including lexical-based and embedding-based. Furthermore. we create a user-friendly interface for the models we included in this\textsc{ CantonMT} research project and make it available to facilitate Cantonese-to-English MT research. Researchers can add more models into this platform via our open-source\textsc{ CantonMT} toolkit \url{https://github.com/kenrickkung/CantoneseTranslation}.

Siwei Wu, Yizhi Li, Yuyang Song et al.

Training agentic models for terminal-based tasks critically depends on high-quality terminal trajectories that capture realistic long-horizon interactions across diverse domains. However, constructing such data at scale remains challenging due to two key requirements: \textbf{\emph{Executability}}, since each instance requires a suitable and often distinct Docker environment; and \textbf{\emph{Verifiability}}, because heterogeneous task outputs preclude unified, standardized verification. To address these challenges, we propose \textbf{TerminalTraj}, a scalable pipeline that (i) filters high-quality repositories to construct Dockerized execution environments, (ii) generates Docker-aligned task instances, and (iii) synthesizes agent trajectories with executable validation code. Using TerminalTraj, we curate 32K Docker images and generate 50,733 verified terminal trajectories across eight domains. Models trained on this data with the Qwen2.5-Coder backbone achieve consistent performance improvements on TerminalBench (TB), with gains of up to 20\% on TB~1.0 and 10\% on TB~2.0 over their respective backbones. Notably, \textbf{TerminalTraj-32B} achieves strong performance among models with fewer than 100B parameters, reaching 35.30\% on TB~1.0 and 22.00\% on TB~2.0, and demonstrates improved test-time scaling behavior. All code and data are available at https://github.com/Wusiwei0410/TerminalTraj.

Hao Li, Yuping Wu, Viktor Schlegel et al.

With the recent advances of large language models (LLMs), it is no longer infeasible to build an automated debate system that helps people to synthesise persuasive arguments. Previous work attempted this task by integrating multiple components. In our work, we introduce an argument mining dataset that captures the end-to-end process of preparing an argumentative essay for a debate, which covers the tasks of claim and evidence identification (Task 1 ED), evidence convincingness ranking (Task 2 ECR), argumentative essay summarisation and human preference ranking (Task 3 ASR) and metric learning for automated evaluation of resulting essays, based on human feedback along argument quality dimensions (Task 4 SQE). Our dataset contains 14k examples of claims that are fully annotated with the various properties supporting the aforementioned tasks. We evaluate multiple generative baselines for each of these tasks, including representative LLMs. We find, that while they show promising results on individual tasks in our benchmark, their end-to-end performance on all four tasks in succession deteriorates significantly, both in automated measures as well as in human-centred evaluation. This challenge presented by our proposed dataset motivates future research on end-to-end argument mining and summarisation. The repository of this project is available at https://github.com/HaoBytes/ArgSum-Datatset

Kung Yin Hong, Lifeng Han, Riza Batista-Navarro et al.

This paper investigates the development and evaluation of machine translation models from Cantonese to English, where we propose a novel approach to tackle low-resource language translations. The main objectives of the study are to develop a model that can effectively translate Cantonese to English and evaluate it against state-of-the-art commercial models. To achieve this, a new parallel corpus has been created by combining different available corpora online with preprocessing and cleaning. In addition, a monolingual Cantonese dataset has been created through web scraping to aid the synthetic parallel corpus generation. Following the data collection process, several approaches, including fine-tuning models, back-translation, and model switch, have been used. The translation quality of models has been evaluated with multiple quality metrics, including lexicon-based metrics (SacreBLEU and hLEPOR) and embedding-space metrics (COMET and BERTscore). Based on the automatic metrics, the best model is selected and compared against the 2 best commercial translators using the human evaluation framework HOPES. The best model proposed in this investigation (NLLB-mBART) with model switch mechanisms has reached comparable and even better automatic evaluation scores against State-of-the-art commercial models (Bing and Baidu Translators), with a SacreBLEU score of 16.8 on our test set. Furthermore, an open-source web application has been developed to allow users to translate between Cantonese and English, with the different trained models available for effective comparisons between models from this investigation and users. CANTONMT is available at https://github.com/kenrickkung/CantoneseTranslation

Hao Li, Yu-Hao Huang, Chang Xu et al.

Time-series Generation (TSG) is a prominent research area with broad applications in simulations, data augmentation, and counterfactual analysis. While existing methods have shown promise in unconditional single-domain TSG, real-world applications demand for cross-domain approaches capable of controlled generation tailored to domain-specific constraints and instance-level requirements. In this paper, we argue that text can provide semantic insights, domain information and instance-specific temporal patterns, to guide and improve TSG. We introduce ``Text-Controlled TSG'', a task focused on generating realistic time series by incorporating textual descriptions. To address data scarcity in this setting, we propose a novel LLM-based Multi-Agent framework that synthesizes diverse, realistic text-to-TS datasets. Furthermore, we introduce BRIDGE, a hybrid text-controlled TSG framework that integrates semantic prototypes with text description for supporting domain-level guidance. This approach achieves state-of-the-art generation fidelity on 11 of 12 datasets, and improves controllability by up to 12% on MSE and 6% MAE compared to no text input generation, highlighting its potential for generating tailored time-series data.

Yizheng Sun, Yanze Xin, Hao Li et al.

Multi-modal Large Language Models (MLLMs) have achieved remarkable success by integrating visual and textual modalities. However, they incur significant computational overhead due to the large number of vision tokens processed, limiting their practicality in resource-constrained environments. We introduce Language-Guided Vision Token Pruning (LVPruning) for MLLMs, an effective yet simple method that significantly reduces the computational burden while preserving model performance. LVPruning employs cross-attention modules to compute the importance of vision tokens based on their interaction with language tokens, determining which to prune. Importantly, LVPruning can be integrated without modifying the original MLLM parameters, which makes LVPruning simple to apply or remove. Our experiments show that LVPruning can effectively reduce up to 90% of vision tokens by the middle layer of LLaVA-1.5, resulting in a 62.1% decrease in inference Tera Floating-Point Operations Per Second (TFLOPs), with an average performance loss of just 0.45% across nine multi-modal benchmarks.

Jincheng Ren, Siwei Wu, Yizhi Li et al.

As model capabilities advance, research has increasingly shifted toward long-horizon, multi-turn terminal-centric agentic tasks, where raw environment feedback is often preserved in the interaction history to support future decisions. However, repeatedly retaining such feedback introduces substantial redundancy and causes cumulative token cost to grow quadratically with the number of steps, hindering long-horizon reasoning. Although observation compression can mitigate this issue, the heterogeneity of terminal environments makes heuristic-based or fixed-prompt methods difficult to generalize. We propose TACO, a plug-and-play, self-evolving Terminal Agent Compression framework that automatically discovers and refines compression rules from interaction trajectories for existing terminal agents. Experiments on TerminalBench (TB 1.0 and TB 2.0) and four additional terminal-related benchmarks (i.e., SWE-Bench Lite, CompileBench, DevEval, and CRUST-Bench) show that TACO consistently improves performance across mainstream agent frameworks and strong backbone models. With MiniMax-2.5, it improves performance on most benchmarks while reducing token overhead by around 10%. On TerminalBench, it brings consistent gains of 1%-4% across strong agentic models, and further improves accuracy by around 2%-3% under the same token budget. These results demonstrate the effectiveness and generalization of self-evolving, task-aware compression for terminal agents.

Hao Li, Viktor Schlegel, Yizheng Sun et al.

Argument Mining (AM), a critical subfield of Natural Language Processing (NLP), focuses on extracting argumentative structures from text. The advent of Large Language Models (LLMs) has profoundly transformed AM, enabling advanced in-context learning, prompt-based generation, and robust cross-domain adaptability. This survey systematically synthesizes recent advancements in LLM-driven AM. We provide a concise review of foundational theories and annotation frameworks, alongside a meticulously curated catalog of datasets. A key contribution is our comprehensive taxonomy of AM subtasks, elucidating how contemporary LLM techniques -- such as prompting, chain-of-thought reasoning, and retrieval augmentation -- have reconfigured their execution. We further detail current LLM architectures and methodologies, critically assess evaluation practices, and delineate pivotal challenges including long-context reasoning, interpretability, and annotation bottlenecks. Conclusively, we highlight emerging trends and propose a forward-looking research agenda for LLM-based computational argumentation, aiming to strategically guide researchers in this rapidly evolving domain.

Tharindu Madusanka, Ian Pratt-Hartmann, Riza Batista-Navarro

Efforts to apply transformer-based language models (TLMs) to the problem of reasoning in natural language have enjoyed ever-increasing success in recent years. The most fundamental task in this area to which nearly all others can be reduced is that of determining satisfiability. However, from a logical point of view, satisfiability problems vary along various dimensions, which may affect TLMs' ability to learn how to solve them. The problem instances of satisfiability in natural language can belong to different computational complexity classes depending on the language fragment in which they are expressed. Although prior research has explored the problem of natural language satisfiability, the above-mentioned point has not been discussed adequately. Hence, we investigate how problem instances from varying computational complexity classes and having different grammatical constructs impact TLMs' ability to learn rules of inference. Furthermore, to faithfully evaluate TLMs, we conduct an empirical study to explore the distribution of satisfiability problems.

Darius Feher, Abdullah Khered, Hao Zhang et al.

In an era increasingly dominated by digital platforms, the spread of misinformation poses a significant challenge, highlighting the need for solutions capable of assessing information veracity. Our research contributes to the field of Explainable Artificial Antelligence (XAI) by developing transformer-based fact-checking models that contextualise and justify their decisions by generating human-accessible explanations. Importantly, we also develop models for automatic evaluation of explanations for fact-checking verdicts across different dimensions such as \texttt{(self)-contradiction}, \texttt{hallucination}, \texttt{convincingness} and \texttt{overall quality}. By introducing human-centred evaluation methods and developing specialised datasets, we emphasise the need for aligning Artificial Intelligence (AI)-generated explanations with human judgements. This approach not only advances theoretical knowledge in XAI but also holds practical implications by enhancing the transparency, reliability and users' trust in AI-driven fact-checking systems. Furthermore, the development of our metric learning models is a first step towards potentially increasing efficiency and reducing reliance on extensive manual assessment. Based on experimental results, our best performing generative model \textsc{ROUGE-1} score of 47.77, demonstrating superior performance in generating fact-checking explanations, particularly when provided with high-quality evidence. Additionally, the best performing metric learning model showed a moderately strong correlation with human judgements on objective dimensions such as \texttt{(self)-contradiction and \texttt{hallucination}, achieving a Matthews Correlation Coefficient (MCC) of around 0.7.}

Hao Li, Yizheng Sun, Viktor Schlegel et al.

Argument summarization aims to generate concise, structured representations of complex, multi-perspective debates. While recent work has advanced the identification and clustering of argumentative components, the generation stage remains underexplored. Existing approaches typically rely on single-pass generation, offering limited support for factual correction or structural refinement. To address this gap, we introduce Arg-LLaDA, a novel large language diffusion framework that iteratively improves summaries via sufficiency-guided remasking and regeneration. Our method combines a flexible masking controller with a sufficiency-checking module to identify and revise unsupported, redundant, or incomplete spans, yielding more faithful, concise, and coherent outputs. Empirical results on two benchmark datasets demonstrate that Arg-LLaDA surpasses state-of-the-art baselines in 7 out of 10 automatic evaluation metrics. In addition, human evaluations reveal substantial improvements across core dimensions, coverage, faithfulness, and conciseness, validating the effectiveness of our iterative, sufficiency-aware generation strategy.

Yizheng Sun, Hao Li, Chang Xu et al.

Vision-Language Models (VLMs) are powerful yet computationally intensive for widespread practical deployments. To address such challenge without costly re-training, post-training acceleration techniques like quantization and token reduction are extensively explored. However, current acceleration evaluations primarily target minimal overall performance degradation, overlooking a crucial question: does the accelerated model still give the same answers to the same questions as it did before acceleration? This is vital for stability-centered industrial applications where consistently correct answers for specific, known situations are paramount, such as in AI-based disease diagnosis. We systematically investigate this for accelerated VLMs, testing four leading models (LLaVA-1.5, LLaVA-Next, Qwen2-VL, Qwen2.5-VL) with eight acceleration methods on ten multi-modal benchmarks. Our findings are stark: despite minimal aggregate performance drops, accelerated models changed original answers up to 20% of the time. Critically, up to 6.5% of these changes converted correct answers to incorrect. Input perturbations magnified these inconsistencies, and the trend is confirmed by case studies with the medical VLM LLaVA-Med. This research reveals a significant oversight in VLM acceleration, stressing an urgent need for instance-level stability checks to ensure trustworthy real-world deployment.

Yulong Wu, Viktor Schlegel, Riza Batista-Navarro

As neural language models achieve human-comparable performance on Machine Reading Comprehension (MRC) and see widespread adoption, ensuring their robustness in real-world scenarios has become increasingly important. Current robustness evaluation research, though, primarily develops synthetic perturbation methods, leaving unclear how well they reflect real life scenarios. Considering this, we present a framework to automatically examine MRC models on naturally occurring textual perturbations, by replacing paragraph in MRC benchmarks with their counterparts based on available Wikipedia edit history. Such perturbation type is natural as its design does not stem from an arteficial generative process, inherently distinct from the previously investigated synthetic approaches. In a large-scale study encompassing SQUAD datasets and various model architectures we observe that natural perturbations result in performance degradation in pre-trained encoder language models. More worryingly, these state-of-the-art Flan-T5 and Large Language Models (LLMs) inherit these errors. Further experiments demonstrate that our findings generalise to natural perturbations found in other more challenging MRC benchmarks. In an effort to mitigate these errors, we show that it is possible to improve the robustness to natural perturbations by training on naturally or synthetically perturbed examples, though a noticeable gap still remains compared to performance on unperturbed data.

Rina Carines Cabral, Soyeon Caren Han, Areej Alhassan et al.

Discontinuous Named Entity Recognition (DNER) presents a challenging problem where entities may be scattered across multiple non-adjacent tokens, making traditional sequence labelling approaches inadequate. Existing methods predominantly rely on custom tagging schemes to handle these discontinuous entities, resulting in models tightly coupled to specific tagging strategies and lacking generalisability across diverse datasets. To address these challenges, we propose TriG-NER, a novel Triplet-Grid Framework that introduces a generalisable approach to learning robust token-level representations for discontinuous entity extraction. Our framework applies triplet loss at the token level, where similarity is defined by word pairs existing within the same entity, effectively pulling together similar and pushing apart dissimilar ones. This approach enhances entity boundary detection and reduces the dependency on specific tagging schemes by focusing on word-pair relationships within a flexible grid structure. We evaluate TriG-NER on three benchmark DNER datasets and demonstrate significant improvements over existing grid-based architectures. These results underscore our framework's effectiveness in capturing complex entity structures and its adaptability to various tagging schemes, setting a new benchmark for discontinuous entity extraction.

Haifa Alrdahi, Riza Batista-Navarro

The chess domain is well-suited for creating an artificial intelligence (AI) system that mimics real-world challenges, including decision-making. Throughout the years, minimal attention has been paid to investigating insights derived from unstructured chess data sources. In this study, we examine the complicated relationships between multiple referenced moves in a chess-teaching textbook, and propose a novel method designed to encapsulate chess knowledge derived from move-action phrases. This study investigates the feasibility of using a modified sentiment analysis method as a means for evaluating chess moves based on text. Our proposed Aspect-Based Sentiment Analysis (ABSA) method represents an advancement in evaluating the sentiment associated with referenced chess moves. By extracting insights from move-action phrases, our approach aims to provide a more fine-grained and contextually aware `chess move'-based sentiment classification. Through empirical experiments and analysis, we evaluate the performance of our fine-tuned ABSA model, presenting results that confirm the efficiency of our approach in advancing aspect-based sentiment classification within the chess domain. This research contributes to the area of game-playing by machines and shows the practical applicability of leveraging NLP techniques to understand the context of strategic games.

Yulong Wu, Viktor Schlegel, Riza Batista-Navarro

How does the natural evolution of context paragraphs affect question answering in generative Large Language Models (LLMs)? To investigate this, we propose a framework for curating naturally evolved, human-edited variants of reading passages from contemporary QA benchmarks and for analyzing LLM performance across a range of semantic similarity scores, which quantify how closely each variant aligns with content seen during pretraining. Using this framework, we evaluate six QA datasets and eight LLMs with publicly available training data. Our experiments reveal that LLM performance declines as reading passages naturally diverge from the versions encountered during pretraining-even when the question and all necessary information remains present at inference time. For instance, average model accuracy on BoolQ drops by over 30% from the highest to lowest similarity bins, with slopes exceeding 70 across several LLMs. These findings suggest that natural text evolution poses a significant challenge to the language understanding capabilities of LLMs.

Hao Li, Viktor Schlegel, Riza Batista-Navarro et al.

Argument summarisation is a promising but currently under-explored field. Recent work has aimed to provide textual summaries in the form of concise and salient short texts, i.e., key points (KPs), in a task known as Key Point Analysis (KPA). One of the main challenges in KPA is finding high-quality key point candidates from dozens of arguments even in a small corpus. Furthermore, evaluating key points is crucial in ensuring that the automatically generated summaries are useful. Although automatic methods for evaluating summarisation have considerably advanced over the years, they mainly focus on sentence-level comparison, making it difficult to measure the quality of a summary (a set of KPs) as a whole. Aggravating this problem is the fact that human evaluation is costly and unreproducible. To address the above issues, we propose a two-step abstractive summarisation framework based on neural topic modelling with an iterative clustering procedure, to generate key points which are aligned with how humans identify key points. Our experiments show that our framework advances the state of the art in KPA, with performance improvement of up to 14 (absolute) percentage points, in terms of both ROUGE and our own proposed evaluation metrics. Furthermore, we evaluate the generated summaries using a novel set-based evaluation toolkit. Our quantitative analysis demonstrates the effectiveness of our proposed evaluation metrics in assessing the quality of generated KPs. Human evaluation further demonstrates the advantages of our approach and validates that our proposed evaluation metric is more consistent with human judgment than ROUGE scores.

Viktor Schlegel, Goran Nenadic, Riza Batista-Navarro

Advances in NLP have yielded impressive results for the task of machine reading comprehension (MRC), with approaches having been reported to achieve performance comparable to that of humans. In this paper, we investigate whether state-of-the-art MRC models are able to correctly process Semantics Altering Modifications (SAM): linguistically-motivated phenomena that alter the semantics of a sentence while preserving most of its lexical surface form. We present a method to automatically generate and align challenge sets featuring original and altered examples. We further propose a novel evaluation methodology to correctly assess the capability of MRC systems to process these examples independent of the data they were optimised on, by discounting for effects introduced by domain shift. In a large-scale empirical study, we apply the methodology in order to evaluate extractive MRC models with regard to their capability to correctly process SAM-enriched data. We comprehensively cover 12 different state-of-the-art neural architecture configurations and four training datasets and find that -- despite their well-known remarkable performance -- optimised models consistently struggle to correctly process semantically altered data.

Viktor Schlegel, Goran Nenadic, Riza Batista-Navarro

Recent years have seen a growing number of publications that analyse Natural Language Inference (NLI) datasets for superficial cues, whether they undermine the complexity of the tasks underlying those datasets and how they impact those models that are optimised and evaluated on this data. This structured survey provides an overview of the evolving research area by categorising reported weaknesses in models and datasets and the methods proposed to reveal and alleviate those weaknesses for the English language. We summarise and discuss the findings and conclude with a set of recommendations for possible future research directions. We hope it will be a useful resource for researchers who propose new datasets, to have a set of tools to assess the suitability and quality of their data to evaluate various phenomena of interest, as well as those who develop novel architectures, to further understand the implications of their improvements with respect to their model's acquired capabilities.

Viktor Schlegel, Marco Valentino, André Freitas et al.

Machine Reading Comprehension (MRC) is the task of answering a question over a paragraph of text. While neural MRC systems gain popularity and achieve noticeable performance, issues are being raised with the methodology used to establish their performance, particularly concerning the data design of gold standards that are used to evaluate them. There is but a limited understanding of the challenges present in this data, which makes it hard to draw comparisons and formulate reliable hypotheses. As a first step towards alleviating the problem, this paper proposes a unifying framework to systematically investigate the present linguistic features, required reasoning and background knowledge and factual correctness on one hand, and the presence of lexical cues as a lower bound for the requirement of understanding on the other hand. We propose a qualitative annotation schema for the first and a set of approximative metrics for the latter. In a first application of the framework, we analyse modern MRC gold standards and present our findings: the absence of features that contribute towards lexical ambiguity, the varying factual correctness of the expected answers and the presence of lexical cues, all of which potentially lower the reading comprehension complexity and quality of the evaluation data.

Gavin Abercrombie, Riza Batista-Navarro

Parliamentary and legislative debate transcripts provide access to information concerning the opinions, positions and policy preferences of elected politicians. They attract attention from researchers from a wide variety of backgrounds, from political and social sciences to computer science. As a result, the problem of automatic sentiment and position-taking analysis has been tackled from different perspectives, using varying approaches and methods, and with relatively little collaboration or cross-pollination of ideas. The existing research is scattered across publications from various fields and venues. In this article we present the results of a systematic literature review of 61 studies, all of which address the automatic analysis of the sentiment and opinions expressed and positions taken by speakers in parliamentary (and other legislative) debates. In this review, we discuss the available research with regard to the aims and objectives of the researchers who work on these problems, the automatic analysis tasks they undertake, and the approaches and methods they use. We conclude by summarizing their findings, discussing the challenges of applying computational analysis to parliamentary debates, and suggesting possible avenues for further research.