This paper investigates the potential benefits of language-specific fact-checking models, focusing on the case of Chinese using CHEF dataset. To better reflect real-world fact-checking, we first develop a novel Chinese document-level evidence retriever, achieving state-of-the-art performance. We then demonstrate the limitations of translation-based methods and multilingual language models, highlighting the need for language-specific systems. To better analyze token-level biases in different systems, we construct an adversarial dataset based on the CHEF dataset, where each instance has a large word overlap with the original one but holds the opposite veracity label. Experimental results on the CHEF dataset and our adversarial dataset show that our proposed method outperforms translation-based methods and multilingual language models and is more robust toward biases, emphasizing the importance of language-specific fact-checking systems.

Research on dialogue constructiveness assessment focuses on (i) analysing conversational factors that influence individuals to take specific actions, win debates, change their perspectives or broaden their open-mindedness and (ii) predicting constructiveness outcomes following dialogues for such use cases. These objectives can be achieved by training either interpretable feature-based models (which often involve costly human annotations) or neural models such as pre-trained language models (which have empirically shown higher task accuracy but lack interpretability). In this paper we propose an LLM feature-based framework for dialogue constructiveness assessment that combines the strengths of feature-based and neural approaches, while mitigating their downsides. The framework first defines a set of dataset-independent and interpretable linguistic features, which can be extracted by both prompting an LLM and simple heuristics. Such features are then used to train LLM feature-based models. We apply this framework to three datasets of dialogue constructiveness and find that our LLM feature-based models outperform or performs at least as well as standard feature-based models and neural models. We also find that the LLM feature-based model learns more robust prediction rules instead of relying on superficial shortcuts, which often trouble neural models.

Active Learning aims to minimize annotation effort by selecting the most useful instances from a pool of unlabeled data. However, typical active learning methods overlook the presence of distinct example groups within a class, whose prevalence may vary, e.g., in occupation classification datasets certain demographics are disproportionately represented in specific classes. This oversight causes models to rely on shortcuts for predictions, i.e., spurious correlations between input attributes and labels occurring in well-represented groups. To address this issue, we propose Active Learning Via INterpolation (ALVIN), which conducts intra-class interpolations between examples from under-represented and well-represented groups to create anchors, i.e., artificial points situated between the example groups in the representation space. By selecting instances close to the anchors for annotation, ALVIN identifies informative examples exposing the model to regions of the representation space that counteract the influence of shortcuts. Crucially, since the model considers these examples to be of high certainty, they are likely to be ignored by typical active learning methods. Experimental results on six datasets encompassing sentiment analysis, natural language inference, and paraphrase detection demonstrate that ALVIN outperforms state-of-the-art active learning methods in both in-distribution and out-of-distribution generalization.

Automated fact-checking systems verify claims against evidence to predict their veracity. In real-world scenarios, the retrieved evidence may not unambiguously support or refute the claim and yield conflicting but valid interpretations. Existing fact-checking datasets assume that the models developed with them predict a single veracity label for each claim, thus discouraging the handling of such ambiguity. To address this issue we present AmbiFC,1 a fact-checking dataset with 10k claims derived from real-world information needs. It contains fine-grained evidence annotations of 50k passages from 5k Wikipedia pages. We analyze the disagreements arising from ambiguity when comparing claims against evidence in AmbiFC, observing a strong correlation of annotator disagreement with linguistic phenomena such as underspecification and probabilistic reasoning. We develop models for predicting veracity handling this ambiguity via soft labels, and find that a pipeline that learns the label distribution for sentence-level evidence selection and veracity prediction yields the best performance. We compare models trained on different subsets of AmbiFC and show that models trained on the ambiguous instances perform better when faced with the identified linguistic phenomena.

Scientific writing is a challenging task, particularly for novice researchers who often rely on feedback from experienced peers. Recent work has primarily focused on improving surface form and style rather than manuscript content. In this paper, we propose a novel task: automated focused feedback generation for scientific writing assistance. We present SWIF²T: a Scientific WrIting Focused Feedback Tool. It is designed to generate specific, actionable and coherent comments, which identify weaknesses in a scientific paper and/or propose revisions to it. Our approach consists of four components - planner, investigator, reviewer and controller - leveraging multiple Large Language Models (LLMs) to implement them. We compile a dataset of 300 peer reviews citing weaknesses in scientific papers and conduct human evaluation. The results demonstrate the superiority in specificity, reading comprehension, and overall helpfulness of SWIF²T’s feedback compared to other approaches. In our analysis, we also identified cases where automatically generated reviews were judged better than human ones, suggesting opportunities for integration of AI-generated feedback in scientific writing.

The recent development of fact verification systems with natural logic has enhanced their explainability by aligning claims with evidence through set-theoretic operators, providing faithful justifications. Despite these advancements, such systems often rely on a large amount of training data annotated with natural logic. To address this issue, we propose a zero-shot method that utilizes the generalization capabilities of instruction-tuned large language models. To comprehensively assess the zero-shot capabilities of our method and other fact verification systems, we evaluate all models on both artificial and real-world claims, including multilingual datasets. We also compare our method against other fact verification systems in two setups. First, in the zero-shot generalization setup, we demonstrate that our approach outperforms other systems that were not specifically trained on natural logic data, achieving an average accuracy improvement of 8.96 points over the best-performing baseline. Second, in the zero-shot transfer setup, we show that current systems trained on natural logic data do not generalize well to other domains, and our method outperforms these systems across all datasets with real-world claims.

Despite progress in automated fact-checking, most systems require a significant amount of labeled training data, which is expensive. In this paper, we propose a novel zero-shot method, which instead of operating directly on the claim and evidence sentences, decomposes them into semantic triples augmented using external knowledge graphs, and uses large language models trained for natural language inference. This allows it to generalize to adversarial datasets and domains that supervised models require specific training data for. Our empirical results show that our approach outperforms previous zero-shot approaches on FEVER, FEVER-Symmetric, FEVER 2.0, and Climate-FEVER, while being comparable or better than supervised models on the adversarial and the out-of-domain datasets.

Active learning for imbalanced classification tasks is challenging as the minority classes naturally occur rarely. Gathering a large pool of unlabelled data is thus essential to capture minority instances. Standard pool-based active learning is computationally expensive on large pools and often reaches low accuracy by overfitting the initial decision boundary, thus failing to explore the input space and find minority instances. To address these issues we propose AnchorAL. At each iteration, AnchorAL chooses class-specific instances from the labelled set, or *anchors*, and retrieves the most similar unlabelled instances from the pool. This resulting *subpool* is then used for active learning. Using a small, fixed-sized subpool AnchorAL allows scaling any active learning strategy to large pools. By dynamically selecting different anchors at each iteration it promotes class balance and prevents overfitting the initial decision boundary, thus promoting the discovery of new clusters of minority instances. Experiments across different classification tasks, active learning strategies, and model architectures AnchorAL is *(i)* faster, often reducing runtime from hours to minutes, *(ii)* trains more performant models, *(iii)* and returns more balanced datasets than competing methods.

The Automated Verification of Textual Claims (AVeriTeC) shared task asks participants to retrieve evidence and predict veracity for real-world claims checked by fact-checkers. Evidence can be found either via a search engine, or via a knowledge store provided by the organisers. Submissions are evaluated using the AVeriTeC score, which considers a claim to be accurately verified if and only if both the verdict is correct and retrieved evidence is considered to meet a certain quality threshold. The shared task received 21 submissions, 18 of which surpassed our baseline. The winning team was TUDA_MAI with an AVeriTeC score of 63%. In this paper we describe the shared task, present the full results, and highlight key takeaways from the shared task.

Uncertainty estimation is an important diagnostic tool for statistical models, and is often used to assess the confidence of model predictions. Previous work shows that neural machine translation (NMT) is an intrinsically uncertain task where there are often multiple correct and semantically equivalent translations, and that well-trained NMT models produce good translations despite spreading probability mass among many semantically similar translations. These findings suggest that popular measures of uncertainty based on token- and sequence-level entropies which measure surface form diversity may not be good proxies of the more useful quantity of interest, semantic diversity. We propose to adapt similarity-sensitive Shannon entropy (S3E), a concept borrowed from theoretical ecology, for NMT. By demonstrating significantly improved correlation between S3E and task performance on quality estimation and named entity recall, we show that S3E is a useful framework for measuring uncertainty in NMT.

Selecting which claims to check is a time-consuming task for human fact-checkers, especially from documents consisting of multiple sentences and containing multiple claims. However, existing claim extraction approaches focus more on identifying and extracting claims from individual sentences, e.g., identifying whether a sentence contains a claim or the exact boundaries of the claim within a sentence. In this paper, we propose a method for document-level claim extraction for fact-checking, which aims to extract check-worthy claims from documents and decontextualise them so that they can be understood out of context. Specifically, we first recast claim extraction as extractive summarization in order to identify central sentences from documents, then rewrite them to include necessary context from the originating document through sentence decontextualisation. Evaluation with both automatic metrics and a fact-checking professional shows that our method is able to extract check-worthy claims from documents at a higher rate than previous work, while also improving evidence retrieval.

Understanding memorisation in language models has practical and societal implications, e.g., studying models’ training dynamics or preventing copyright infringements.Prior work defines memorisation as the causal effect of training with an instance on the model’s ability to predict that instance. This definition relies on a counterfactual: the ability to observe what would have happened had the model not seen that instance.Existing methods struggle to provide computationally efficient and accurate estimates of this counterfactual. Further, they often estimate memorisation for a model architecture rather than for a specific model instance. This paper fills an important gap in the literature, proposing a new, principled, and efficient method to estimate memorisation based on the difference-in-differences design from econometrics. Using this method, we characterise a model’s memorisation profile–its memorisation trends across training–by only observing its behaviour on a small set of instances throughout training.In experiments with the Pythia model suite, we find that memorisation (i) is stronger and more persistent in larger models, (ii) is determined by data order and learning rate, and (iii) has stable trends across model sizes, thus making memorisation in larger models predictable from smaller ones.

Natural language inference (NLI) models are susceptible to learning shortcuts, i.e. decision rules that spuriously correlate with the label. As a result, they achieve high in-distribution performance, but fail to generalize to out-of-distribution samples where such correlations do not hold. In this paper, we present a training method to reduce the reliance of NLI models on shortcuts and improve their out-of-distribution performance without assuming prior knowledge of the shortcuts being targeted. To this end, we propose a minimax objective between a learner model being trained for the NLI task, and an auxiliary model aiming to maximize the learner’s loss by up-weighting examples from regions of the input space where the learner incurs high losses. This process incentivizes the learner to focus on under-represented “hard” examples with patterns that contradict the shortcuts learned from the prevailing “easy” examples. Experimental results on three NLI datasets demonstrate that our method consistently outperforms other robustness enhancing techniques on out-of-distribution adversarial test sets, while maintaining high in-distribution accuracy.

Misinformation is often conveyed in multiple modalities, e.g. a miscaptioned image. Multimodal misinformation is perceived as more credible by humans, and spreads faster than its text-only counterparts. While an increasing body of research investigates automated fact-checking (AFC), previous surveys mostly focus on text. In this survey, we conceptualise a framework for AFC including subtasks unique to multimodal misinformation. Furthermore, we discuss related terms used in different communities and map them to our framework. We focus on four modalities prevalent in real-world fact-checking: text, image, audio, and video. We survey benchmarks and models, and discuss limitations and promising directions for future research

Automated fact-checking is often presented as an epistemic tool that fact-checkers, social media consumers, and other stakeholders can use to fight misinformation. Nevertheless, few papers thoroughly discuss how. We document this by analysing 100 highly-cited papers, and annotating epistemic elements related to intended use, i.e., means, ends, and stakeholders. We find that narratives leaving out some of these aspects are common, that many papers propose inconsistent means and ends, and that the feasibility of suggested strategies rarely has empirical backing. We argue that this vagueness actively hinders the technology from reaching its goals, as it encourages overclaiming, limits criticism, and prevents stakeholder feedback. Accordingly, we provide several recommendations for thinking and writing about the use of fact-checking artefacts.

Fact verification systems assess a claim’s veracity based on evidence. An important consideration in designing them is faithfulness, i.e. generating explanations that accurately reflect the reasoning of the model. Recent works have focused on natural logic, which operates directly on natural language by capturing the semantic relation of spans between an aligned claim with its evidence via set-theoretic operators. However, these approaches rely on substantial resources for training, which are only available for high-resource languages. To this end, we propose to use question answering to predict natural logic operators, taking advantage of the generalization capabilities of instruction-tuned language models. Thus, we obviate the need for annotated training data while still relying on a deterministic inference system. In a few-shot setting on FEVER, our approach outperforms the best baseline by 4.3 accuracy points, including a state-of-the-art pre-trained seq2seq natural logic system, as well as a state-of-the-art prompt-based classifier. Our system demonstrates its robustness and portability, achieving competitive performance on a counterfactual dataset and surpassing all approaches without further annotation on a Danish verification dataset. A human evaluation indicates that our approach produces more plausible proofs with fewer erroneous natural logic operators than previous natural logic-based systems.

Minimum Bayes risk (MBR) decoding outputs the hypothesis with the highest expected utility over the model distribution for some utility function. It has been shown to improve accuracy over beam search in conditional language generation problems and especially neural machine translation, in both human and automatic evaluations. However, the standard sampling-based algorithm for MBR is substantially more computationally expensive than beam search, requiring a large number of samples as well as a quadratic number of calls to the utility function, limiting its applicability. We describe an algorithm for MBR which gradually grows the number of samples used to estimate the utility while pruning hypotheses that are unlikely to have the highest utility according to confidence estimates obtained with bootstrap sampling. Our method requires fewer samples and drastically reduces the number of calls to the utility function compared to standard MBR while being statistically indistinguishable in terms of accuracy. We demonstrate the effectiveness of our approach in experiments on three language pairs, using chrF++ and COMET as utility/evaluation metrics.

Prior research has shown that typical fact-checking models for stand-alone claims struggle with claims made in conversation. As a solution, fine-tuning these models on dialogue data has been proposed. However, creating separate models for each use case is impractical, and we show that fine-tuning models for dialogue results in poor performance on typical fact-checking. To overcome this challenge, we present techniques that allow us to use the same models for both dialogue and typical fact-checking. These mainly focus on retrieval adaptation and transforming conversational inputs so that they can be accurately processed by models trained on stand-alone claims. We demonstrate that a typical fact-checking model incorporating these techniques is competitive with state-of-the-art models for dialogue, while maintaining its performance on stand-alone claims.

The healthcare domain suffers from the spread of poor quality articles on the Internet. While manual efforts exist to check the quality of online healthcare articles, they are not sufficient to assess all those in circulation. Such quality assessment can be automated as a text classification task, however, explanations for the labels are necessary for the users to trust the model predictions. While current explainable systems tackle explanation generation as summarization, we propose a new approach based on question answering (QA) that allows us to generate explanations for multiple criteria using a single model. We show that this QA-based approach is competitive with the current state-of-the-art, and complements summarization-based models for explainable quality assessment. We also introduce a human evaluation protocol more appropriate than automatic metrics for the evaluation of explanation generation models.

Detecting biased language is useful for a variety of applications, such as identifying hyperpartisan news sources or flagging one-sided rhetoric. In this work we introduce WikiEvolve, a dataset for document-level promotional tone detection. Unlike previously proposed datasets, WikiEvolve contains seven versions of the same article from Wikipedia, from different points in its revision history; one with promotional tone, and six without it. This allows for obtaining more precise training signal for learning models from promotional tone detection. We adapt the previously proposed gradient reversal layer framework to encode two article versions simultaneously and thus leverage this additional training signal. In our experiments, our proposed adaptation of gradient reversal improves the accuracy of four different architectures on both in-domain and out-of-domain evaluation.

People leverage group discussions to collaborate in order to solve complex tasks, e.g. in project meetings or hiring panels. By doing so, they engage in a variety of conversational strategies where they try to convince each other of the best approach and ultimately reach a decision. In this work, we investigate methods for detecting what makes someone change their mind. To this end, we leverage a recently introduced dataset containing group discussions of people collaborating to solve a task. To find out what makes someone change their mind, we incorporate various techniques such as neural text classification and language-agnostic change point detection. Evaluation of these methods shows that while the task is not trivial, the best way to approach it is using a language-aware model with learning-to-rank training. Finally, we examine the cues that the models develop as indicative of the cause of a change of mind.

Fact-checking requires retrieving evidence related to a claim under investigation. The task can be formulated as question generation based on a claim, followed by question answering.However, recent question generation approaches assume that the answer is known and typically contained in a passage given as input,whereas such passages are what is being sought when verifying a claim.In this paper, we present Varifocal, a method that generates questions based on different focal points within a given claim, i.e. different spans of the claim and its metadata, such as its source and date.Our method outperforms previous work on a fact-checking question generation dataset on a wide range of automatic evaluation metrics.These results are corroborated by our manual evaluation, which indicates that our method generates more relevant and informative questions.We further demonstrate the potential of focal points in generating sets of clarification questions for product descriptions.

Disagreements are frequently studied from the perspective of either detecting toxicity or analysing argument structure. We propose a framework of dispute tactics which unifies these two perspectives, as well as other dialogue acts which play a role in resolving disputes, such as asking questions and providing clarification. This framework includes a preferential ordering among rebuttal-type tactics, ranging from ad hominem attacks to refuting the central argument. Using this framework, we annotate 213 disagreements (3,865 utterances) from Wikipedia Talk pages. This allows us to investigate research questions around the tactics used in disagreements; for instance, we provide empirical validation of the approach to disagreement recommended by Wikipedia. We develop models for multilabel prediction of dispute tactics in an utterance, achieving the best performance with a transformer-based label powerset model. Adding an auxiliary task to incorporate the ordering of rebuttal tactics further yields a statistically significant increase. Finally, we show that these annotations can be used to provide useful additional signals to improve performance on the task of predicting escalation.

A key component of fact verification is the evidence retrieval, often from multiple documents. Recent approaches use dense representations and condition the retrieval of each document on the previously retrieved ones. The latter step is performed over all the documents in the collection, requiring storing their dense representations in an index, thus incurring a high memory footprint. An alternative paradigm is retrieve-and-rerank, where documents are retrieved using methods such as BM25, their sentences are reranked, and further documents are retrieved conditioned on these sentences, reducing the memory requirements. However, such approaches can be brittle as they rely on heuristics and assume hyperlinks between documents.We propose a novel retrieve-and-rerank method for multi-hop retrieval, that consists of a retriever that jointly scores documents in the knowledge source and sentences from previously retrieved documents using an autoregressive formulation and is guided by a proof system based on natural logic that dynamically terminates the retrieval process if the evidence is deemed sufficient.This method exceeds or is on par with the current state-of-the-art on FEVER, HoVer and FEVEROUS-S, while using 5 to 10 times less memory than competing systems. Evaluation on an adversarial dataset indicates improved stability of our approach compared to commonly deployed threshold-based methods. Finally, the proof system helps humans predict model decisions correctly more often than using the evidence alone.

Recent research on argumentative dialogues has focused on persuading people to take some action, changing their stance on the topic of discussion, or winning debates. In this work, we focus on argumentative dialogues that aim to open up (rather than change) people’s minds to help them become more understanding to views that are unfamiliar or in opposition to their own convictions. To this end, we present a dataset of 183 argumentative dialogues about 3 controversial topics: veganism, Brexit and COVID-19 vaccination. The dialogues were collected using the Wizard of Oz approach, where wizards leverage a knowledge-base of arguments to converse with participants. Open-mindedness is measured before and after engaging in the dialogue using a questionnaire from the psychology literature, and success of the dialogue is measured as the change in the participant’s stance towards those who hold opinions different to theirs. We evaluate two dialogue models: a Wikipedia-based and an argument-based model. We show that while both models perform closely in terms of opening up minds, the argument-based model is significantly better on other dialogue properties such as engagement and clarity.

Despite strong performance in many sequence-to-sequence tasks, autoregressive models trained with maximum likelihood estimation suffer from exposure bias, i.e. the discrepancy between the ground-truth prefixes used during training and the model-generated prefixes used at inference time. Scheduled sampling is a simple and empirically successful approach which addresses this issue by incorporating model-generated prefixes into training. However, it has been argued that it is an inconsistent training objective leading to models ignoring the prefixes altogether. In this paper, we conduct systematic experiments and find that scheduled sampling, while it ameliorates exposure bias by increasing model reliance on the input sequence, worsens performance when the prefix at inference time is correct, a form of catastrophic forgetting. We propose to use Elastic Weight Consolidation to better balance mitigating exposure bias with retaining performance. Experiments on four IWSLT’14 and WMT’14 translation datasets demonstrate that our approach alleviates catastrophic forgetting and significantly outperforms maximum likelihood estimation and scheduled sampling baselines.

Fact-checking has become increasingly important due to the speed with which both information and misinformation can spread in the modern media ecosystem. Therefore, researchers have been exploring how fact-checking can be automated, using techniques based on natural language processing, machine learning, knowledge representation, and databases to automatically predict the veracity of claims. In this paper, we survey automated fact-checking stemming from natural language processing, and discuss its connections to related tasks and disciplines. In this process, we present an overview of existing datasets and models, aiming to unify the various definitions given and identify common concepts. Finally, we highlight challenges for future research.

Fact verification systems typically rely on neural network classifiers for veracity prediction, which lack explainability. This paper proposes ProoFVer, which uses a seq2seq model to generate natural logic-based inferences as proofs. These proofs consist of lexical mutations between spans in the claim and the evidence retrieved, each marked with a natural logic operator. Claim veracity is determined solely based on the sequence of these operators. Hence, these proofs are faithful explanations, and this makes ProoFVer faithful by construction. Currently, ProoFVer has the highest label accuracy and the second best score in the FEVER leaderboard. Furthermore, it improves by 13.21% points over the next best model on a dataset with counterfactual instances, demonstrating its robustness. As explanations, the proofs show better overlap with human rationales than attention-based highlights and the proofs help humans predict model decisions correctly more often than using the evidence directly.1

A common issue in real-world applications of named entity recognition and classification (NERC) is the absence of annotated data for the target entity classes during training. Zero-shot learning approaches address this issue by learning models from classes with training data that can predict classes without it. This paper presents the first approach for zero-shot NERC, introducing novel architectures that leverage the fact that textual descriptions for many entity classes occur naturally. We address the zero-shot NERC specific challenge that the not-an-entity class is not well defined as different entity classes are considered in training and testing. For evaluation, we adapt two datasets, OntoNotes and MedMentions, emulating the difficulty of real-world zero-shot learning by testing models on the rarest entity classes. Our proposed approach outperforms baselines adapted from machine reading comprehension and zero-shot text classification. Furthermore, we assess the effect of different class descriptions for this task.

This paper introduces the task of factual error correction: performing edits to a claim so that the generated rewrite is better supported by evidence. This extends the well-studied task of fact verification by providing a mechanism to correct written texts that are refuted or only partially supported by evidence. We demonstrate that it is feasible to train factual error correction systems from existing fact checking datasets which only contain labeled claims accompanied by evidence, but not the correction. We achieve this by employing a two-stage distant supervision approach that incorporates evidence into masked claims when generating corrections. Our approach, based on the T5 transformer and using retrieved evidence, achieved better results than existing work which used a pointer copy network and gold evidence, producing accurate factual error corrections for 5x more instances in human evaluation and a .125 increase in SARI score. The evaluation is conducted on a dataset of 65,000 instances based on a recent fact verification shared task and we release it to enable further work on the task.

The Fact Extraction and VERification Over Unstructured and Structured information (FEVEROUS) shared task, asks participating systems to determine whether human-authored claims are Supported or Refuted based on evidence retrieved from Wikipedia (or NotEnoughInfo if the claim cannot be verified). Compared to the FEVER 2018 shared task, the main challenge is the addition of structured data (tables and lists) as a source of evidence. The claims in the FEVEROUS dataset can be verified using only structured evidence, only unstructured evidence, or a mixture of both. Submissions are evaluated using the FEVEROUS score that combines label accuracy and evidence retrieval. Unlike FEVER 2018, FEVEROUS requires partial evidence to be returned for NotEnoughInfo claims, and the claims are longer and thus more complex. The shared task received 13 entries, six of which were able to beat the baseline system. The winning team was “Bust a move!”, achieving a FEVEROUS score of 27% (+9% compared to the baseline). In this paper we describe the shared task, present the full results and highlight commonalities and innovations among the participating systems.

The biases present in training datasets have been shown to affect models for sentence pair classification tasks such as natural language inference (NLI) and fact verification. While fine-tuning models on additional data has been used to mitigate them, a common issue is that of catastrophic forgetting of the original training dataset. In this paper, we show that elastic weight consolidation (EWC) allows fine-tuning of models to mitigate biases while being less susceptible to catastrophic forgetting. In our evaluation on fact verification and NLI stress tests, we show that fine-tuning with EWC dominates standard fine-tuning, yielding models with lower levels of forgetting on the original (biased) dataset for equivalent gains in accuracy on the fine-tuning (unbiased) dataset.

Disagreements are pervasive in human communication. In this paper we investigate what makes disagreement constructive. To this end, we construct WikiDisputes, a corpus of 7425 Wikipedia Talk page conversations that contain content disputes, and define the task of predicting whether disagreements will be escalated to mediation by a moderator. We evaluate feature-based models with linguistic markers from previous work, and demonstrate that their performance is improved by using features that capture changes in linguistic markers throughout the conversations, as opposed to averaged values. We develop a variety of neural models and show that taking into account the structure of the conversation improves predictive accuracy, exceeding that of feature-based models. We assess our best neural model in terms of both predictive accuracy and uncertainty by evaluating its behaviour when it is only exposed to the beginning of the conversation, finding that model accuracy improves and uncertainty reduces as models are exposed to more information.

The performance of natural language generation systems has improved substantially with modern neural networks. At test time they typically employ beam search to avoid locally optimal but globally suboptimal predictions. However, due to model errors, a larger beam size can lead to deteriorating performance according to the evaluation metric. For this reason, it is common to rerank the output of beam search, but this relies on beam search to produce a good set of hypotheses, which limits the potential gains. Other alternatives to beam search require changes to the training of the model, which restricts their applicability compared to beam search. This paper proposes incremental beam manipulation, i.e. reranking the hypotheses in the beam during decoding instead of only at the end. This way, hypotheses that are unlikely to lead to a good final output are discarded, and in their place hypotheses that would have been ignored will be considered instead. Applying incremental beam manipulation leads to an improvement of 1.93 and 5.82 BLEU points over vanilla beam search for the test sets of the E2E and WebNLG challenges respectively. The proposed method also outperformed a strong reranker by 1.04 BLEU points on the E2E challenge, while being on par with it on the WebNLG dataset.

Word embedding learning methods require a large number of occurrences of a word to accurately learn its embedding. However, out-of-vocabulary (OOV) words which do not appear in the training corpus emerge frequently in the smaller downstream data. Recent work formulated OOV embedding learning as a few-shot regression problem and demonstrated that meta-learning can improve results obtained. However, the algorithm used, model-agnostic meta-learning (MAML) is known to be unstable and perform worse when a large number of gradient steps are used for parameter updates. In this work, we propose the use of Leap, a meta-learning algorithm which leverages the entire trajectory of the learning process instead of just the beginning and the end points, and thus ameliorates these two issues. In our experiments on a benchmark OOV embedding learning dataset and in an extrinsic evaluation, Leap performs comparably or better than MAML. We go on to examine which contexts are most beneficial to learn an OOV embedding from, and propose that the choice of contexts may matter more than the meta-learning employed.

Policy compliance detection is the task of ensuring that a scenario conforms to a policy (e.g. a claim is valid according to government rules or a post in an online platform conforms to community guidelines). This task has been previously instantiated as a form of textual entailment, which results in poor accuracy due to the complexity of the policies. In this paper we propose to address policy compliance detection via decomposing it into question answering, where questions check whether the conditions stated in the policy apply to the scenario, and an expression tree combines the answers to obtain the label. Despite the initial upfront annotation cost, we demonstrate that this approach results in better accuracy, especially in the cross-policy setup where the policies during testing are unseen in training. In addition, it allows us to use existing question answering models pre-trained on existing large datasets. Finally, it explicitly identifies the information missing from a scenario in case policy compliance cannot be determined. We conduct our experiments using a recent dataset consisting of government policies, which we augment with expert annotations and find that the cost of annotating question answering decomposition is largely offset by improved inter-annotator agreement and speed.

Fact checking at scale is difficult—while the number of active fact checking websites is growing, it remains too small for the needs of the contemporary media ecosystem. However, despite good intentions, contributions from volunteers are often error-prone, and thus in practice restricted to claim detection. We investigate how to increase the accuracy and efficiency of fact checking by providing information about the claim before performing the check, in the form of natural language briefs. We investigate passage-based briefs, containing a relevant passage from Wikipedia, entity-centric ones consisting of Wikipedia pages of mentioned entities, and Question-Answering Briefs, with questions decomposing the claim, and their answers. To produce QABriefs, we develop QABriefer, a model that generates a set of questions conditioned on the claim, searches the web for evidence, and generates answers. To train its components, we introduce QABriefDataset We show that fact checking with briefs — in particular QABriefs — increases the accuracy of crowdworkers by 10% while slightly decreasing the time taken. For volunteer (unpaid) fact checkers, QABriefs slightly increase accuracy and reduce the time required by around 20%.

There has been substantial progress in summarization research enabled by the availability of novel, often large-scale, datasets and recent advances on neural network-based approaches. However, manual evaluation of the system generated summaries is inconsistent due to the difficulty the task poses to human non-expert readers. To address this issue, we propose a novel approach for manual evaluation, Highlight-based Reference-less Evaluation of Summarization (HighRES), in which summaries are assessed by multiple annotators against the source document via manually highlighted salient content in the latter. Thus summary assessment on the source document by human judges is facilitated, while the highlights can be used for evaluating multiple systems. To validate our approach we employ crowd-workers to augment with highlights a recently proposed dataset and compare two state-of-the-art systems. We demonstrate that HighRES improves inter-annotator agreement in comparison to using the source document directly, while they help emphasize differences among systems that would be ignored under other evaluation approaches.

Named entity recognition (NER) is one of the best studied tasks in natural language processing. However, most approaches are not capable of handling nested structures which are common in many applications. In this paper we introduce a novel neural network architecture that first merges tokens and/or entities into entities forming nested structures, and then labels each of them independently. Unlike previous work, our merge and label approach predicts real-valued instead of discrete segmentation structures, which allow it to combine word and nested entity embeddings while maintaining differentiability. We evaluate our approach using the ACE 2005 Corpus, where it achieves state-of-the-art F1 of 74.6, further improved with contextual embeddings (BERT) to 82.4, an overall improvement of close to 8 F1 points over previous approaches trained on the same data. Additionally we compare it against BiLSTM-CRFs, the dominant approach for flat NER structures, demonstrating that its ability to predict nested structures does not impact performance in simpler cases.

In this paper we frame the task of supervised relation classification as an instance of meta-learning. We propose a model-agnostic meta-learning protocol for training relation classifiers to achieve enhanced predictive performance in limited supervision settings. During training, we aim to not only learn good parameters for classifying relations with sufficient supervision, but also learn model parameters that can be fine-tuned to enhance predictive performance for relations with limited supervision. In experiments conducted on two relation classification datasets, we demonstrate that the proposed meta-learning approach improves the predictive performance of two state-of-the-art supervised relation classification models.

The task of Natural Language Inference (NLI) is widely modeled as supervised sentence pair classification. While there has been a lot of work recently on generating explanations of the predictions of classifiers on a single piece of text, there have been no attempts to generate explanations of classifiers operating on pairs of sentences. In this paper, we show that it is possible to generate token-level explanations for NLI without the need for training data explicitly annotated for this purpose. We use a simple LSTM architecture and evaluate both LIME and Anchor explanations for this task. We compare these to a Multiple Instance Learning (MIL) method that uses thresholded attention make token-level predictions. The approach we present in this paper is a novel extension of zero-shot single-sentence tagging to sentence pairs for NLI. We conduct our experiments on the well-studied SNLI dataset that was recently augmented with manually annotation of the tokens that explain the entailment relation. We find that our white-box MIL-based method, while orders of magnitude faster, does not reach the same accuracy as the black-box methods.

Complex Word Identification (CWI) is the task of identifying which words or phrases in a sentence are difficult to understand by a target audience. The latest CWI Shared Task released data for two settings: monolingual (i.e. train and test in the same language) and cross-lingual (i.e. test in a language not seen during training). The best monolingual models relied on language-dependent features, which do not generalise in the cross-lingual setting, while the best cross-lingual model used neural networks with multi-task learning. In this paper, we present monolingual and cross-lingual CWI models that perform as well as (or better than) most models submitted to the latest CWI Shared Task. We show that carefully selected features and simple learning models can achieve state-of-the-art performance, and result in strong baselines for future development in this area. Finally, we discuss how inconsistencies in the annotation of the data can explain some of the results obtained.

Rhetorical structure trees have been shown to be useful for several document-level tasks including summarization and document classification. Previous approaches to RST parsing have used discriminative models; however, these are less sample efficient than generative models, and RST parsing datasets are typically small. In this paper, we present the first generative model for RST parsing. Our model is a document-level RNN grammar (RNNG) with a bottom-up traversal order. We show that, for our parser’s traversal order, previous beam search algorithms for RNNGs have a left-branching bias which is ill-suited for RST parsing. We develop a novel beam search algorithm that keeps track of both structure-and word-generating actions without exhibit-ing this branching bias and results in absolute improvements of 6.8 and 2.9 on unlabelled and labelled F1 over previous algorithms. Overall, our generative model outperforms a discriminative model with the same features by 2.6 F1points and achieves performance comparable to the state-of-the-art, outperforming all published parsers from a recent replication study that do not use additional training data

Automated fact verification has been progressing owing to advancements in modeling and availability of large datasets. Due to the nature of the task, it is critical to understand the vulnerabilities of these systems against adversarial instances designed to make them predict incorrectly. We introduce two novel scoring metrics, attack potency and system resilience which take into account the correctness of the adversarial instances, an aspect often ignored in adversarial evaluations. We consider six fact verification systems from the recent Fact Extraction and VERification (FEVER) challenge: the four best-scoring ones and two baselines. We evaluate adversarial instances generated by a recently proposed state-of-the-art method, a paraphrasing method, and rule-based attacks devised for fact verification. We find that our rule-based attacks have higher potency, and that while the rankings among the top systems changed, they exhibited higher resilience than the baselines.

Stance detection in social media is a well-studied task in a variety of domains. Nevertheless, previous work has mostly focused on multiclass versions of the problem, where the labels are mutually exclusive, and typically positive, negative or neutral. In this paper, we address versions of the task in which an utterance can have multiple labels, thus corresponding to multilabel classification. We propose a method that explicitly incorporates label dependencies in the training objective and compare it against a variety of baselines, as well as a reduction of multilabel to multiclass learning. In experiments with three datasets, we find that our proposed method improves upon all baselines on two out of three datasets. We also show that the reduction of multilabel to multiclass classification can be very competitive, especially in cases where the output consists of a small number of labels and one can enumerate over all label combinations.

We present the results of the second Fact Extraction and VERification (FEVER2.0) Shared Task. The task challenged participants to both build systems to verify factoid claims using evidence retrieved from Wikipedia and to generate adversarial attacks against other participant’s systems. The shared task had three phases: building, breaking and fixing. There were 8 systems in the builder’s round, three of which were new qualifying submissions for this shared task, and 5 adversaries generated instances designed to induce classification errors and one builder submitted a fixed system which had higher FEVER score and resilience than their first submission. All but one newly submitted systems attained FEVER scores higher than the best performing system from the first shared task and under adversarial evaluation, all systems exhibited losses in FEVER score. There was a great variety in adversarial attack types as well as the techniques used to generate the attacks, In this paper, we present the results of the shared task and a summary of the systems, highlighting commonalities and innovations among participating systems.

Most existing relation extraction models assume a fixed set of relations and are unable to adapt to exploit newly available supervision data to extract new relations. In order to alleviate such problems, there is the need to develop approaches that make relation extraction models capable of continuous adaptation and learning. We investigate and present results for such an approach, based on a combination of ideas from lifelong learning and optimization-based meta-learning. We evaluate the proposed approach on two recent lifelong relation extraction benchmarks, and demonstrate that it markedly outperforms current state-of-the-art approaches.

In this paper we introduce a new publicly available dataset for verification against textual sources, FEVER: Fact Extraction and VERification. It consists of 185,445 claims generated by altering sentences extracted from Wikipedia and subsequently verified without knowledge of the sentence they were derived from. The claims are classified as Supported, Refuted or NotEnoughInfo by annotators achieving 0.6841 in Fleiss kappa. For the first two classes, the annotators also recorded the sentence(s) forming the necessary evidence for their judgment. To characterize the challenge of the dataset presented, we develop a pipeline approach and compare it to suitably designed oracles. The best accuracy we achieve on labeling a claim accompanied by the correct evidence is 31.87%, while if we ignore the evidence we achieve 50.91%. Thus we believe that FEVER is a challenging testbed that will help stimulate progress on claim verification against textual sources.

Approaches to authorship attribution, the task of identifying the author of a document, are based on analysis of individuals’ writing style and/or preferred topics. Although the problem has been widely explored, no previous studies have analysed the relationship between dataset characteristics and effectiveness of different types of features. This study carries out an analysis of four widely used datasets to explore how different types of features affect authorship attribution accuracy under varying conditions. The results of the analysis are applied to authorship attribution models based on both discrete and continuous representations. We apply the conclusions from our analysis to an extension of an existing approach to authorship attribution and outperform the prior state-of-the-art on two out of the four datasets used.

The recently increased focus on misinformation has stimulated research in fact checking, the task of assessing the truthfulness of a claim. Research in automating this task has been conducted in a variety of disciplines including natural language processing, machine learning, knowledge representation, databases, and journalism. While there has been substantial progress, relevant papers and articles have been published in research communities that are often unaware of each other and use inconsistent terminology, thus impeding understanding and further progress. In this paper we survey automated fact checking research stemming from natural language processing and related disciplines, unifying the task formulations and methodologies across papers and authors. Furthermore, we highlight the use of evidence as an important distinguishing factor among them cutting across task formulations and methods. We conclude with proposing avenues for future NLP research on automated fact checking.

We present the results of the first Fact Extraction and VERification (FEVER) Shared Task. The task challenged participants to classify whether human-written factoid claims could be SUPPORTED or REFUTED using evidence retrieved from Wikipedia. We received entries from 23 competing teams, 19 of which scored higher than the previously published baseline. The best performing system achieved a FEVER score of 64.21%. In this paper, we present the results of the shared task and a summary of the systems, highlighting commonalities and innovations among participating systems.

We consider the task of relation classification, and pose this task as one of textual entailment. We show that this formulation leads to several advantages, including the ability to (i) perform zero-shot relation classification by exploiting relation descriptions, (ii) utilize existing textual entailment models, and (iii) leverage readily available textual entailment datasets, to enhance the performance of relation classification systems. Our experiments show that the proposed approach achieves 20.16% and 61.32% in F1 zero-shot classification performance on two datasets, which further improved to 22.80% and 64.78% respectively with the use of conditional encoding.

Recent work on abstractive summarization has made progress with neural encoder-decoder architectures. However, such models are often challenged due to their lack of explicit semantic modeling of the source document and its summary. In this paper, we extend previous work on abstractive summarization using Abstract Meaning Representation (AMR) with a neural language generation stage which we guide using the source document. We demonstrate that this guidance improves summarization results by 7.4 and 10.5 points in ROUGE-2 using gold standard AMR parses and parses obtained from an off-the-shelf parser respectively. We also find that the summarization performance on later parses is 2 ROUGE-2 points higher than that of a well-established neural encoder-decoder approach trained on a larger dataset.

This paper describes the submission by the University of Sheffield to the SemEval 2017 Abstract Meaning Representation Parsing and Generation task (SemEval 2017 Task 9, Subtask 2). We cast language generation from AMR as a sequence of actions (e.g., insert/remove/rename edges and nodes) that progressively transform the AMR graph into a dependency parse tree. This transition-based approach relies on the fact that an AMR graph can be considered structurally similar to a dependency tree, with a focus on content rather than function words. An added benefit to this approach is the greater amount of data we can take advantage of to train the parse-to-text linearizer. Our submitted run on the test data achieved a BLEU score of 3.32 and a Trueskill score of -22.04 on automatic and human evaluation respectively.

This paper presents work on using continuous representations for authorship attribution. In contrast to previous work, which uses discrete feature representations, our model learns continuous representations for n-gram features via a neural network jointly with the classification layer. Experimental results demonstrate that the proposed model outperforms the state-of-the-art on two datasets, while producing comparable results on the remaining two.

In this paper we present our automated fact checking system demonstration which we developed in order to participate in the Fast and Furious Fact Check challenge. We focused on simple numerical claims such as “population of Germany in 2015 was 80 million” which comprised a quarter of the test instances in the challenge, achieving 68% accuracy. Our system extends previous work on semantic parsing and claim identification to handle temporal expressions and knowledge bases consisting of multiple tables, while relying solely on automatically generated training data. We demonstrate the extensible nature of our system by evaluating it on relations used in previous work. We make our system publicly available so that it can be used and extended by the community.

We present the first prototype of the SUMMA Platform: an integrated platform for multilingual media monitoring. The platform contains a rich suite of low-level and high-level natural language processing technologies: automatic speech recognition of broadcast media, machine translation, automated tagging and classification of named entities, semantic parsing to detect relationships between entities, and automatic construction / augmentation of factual knowledge bases. Implemented on the Docker platform, it can easily be deployed, customised, and scaled to large volumes of incoming media streams.

Imitation learning is a learning paradigm originally developed to learn robotic controllers from demonstrations by humans, e.g. autonomous flight from pilot demonstrations. Recently, algorithms for structured prediction were proposed under this paradigm and have been applied successfully to a number of tasks including syntactic dependency parsing, information extraction, coreference resolution, dynamic feature selection, semantic parsing and natural language generation. Key advantages are the ability to handle large output search spaces and to learn with non-decomposable loss functions. Our aim in this tutorial is to have a unified presentation of the various imitation algorithms for structure prediction, and show how they can be applied to a variety of NLP tasks.All material associated with the tutorial will be made available through https://sheffieldnlp.github.io/ImitationLearningTutorialEACL2017/.

Fake news has become a hotly debated topic in journalism. In this paper, we present our entry to the 2017 Fake News Challenge which models the detection of fake news as a stance classification task that finished in 11th place on the leader board. Our entry is an ensemble system of classifiers developed by students in the context of their coursework. We show how we used the stacking ensemble method for this purpose and obtained improvements in classification accuracy exceeding each of the individual models’ performance on the development data. Finally, we discuss aspects of the experimental setup of the challenge.

Natural language generation (NLG) is the task of generating natural language from a meaning representation. Current rule-based approaches require domain-specific and manually constructed linguistic resources, while most machine-learning based approaches rely on aligned training data and/or phrase templates. The latter are needed to restrict the search space for the structured prediction task defined by the unaligned datasets. In this work we propose the use of imitation learning for structured prediction which learns an incremental model that handles the large search space by avoiding explicit enumeration of the outputs. We focus on the Locally Optimal Learning to Search framework which allows us to train against non-decomposable loss functions such as the BLEU or ROUGE scores while not assuming gold standard alignments. We evaluate our approach on three datasets using both automatic measures and human judgements and achieve results comparable to the state-of-the-art approaches developed for each of them.

Semantic parsing is the task of translating natural language utterances into a machine-interpretable meaning representation. Most approaches to this task have been evaluated on a small number of existing corpora which assume that all utterances must be interpreted according to a database and typically ignore context. In this paper we present a new, publicly available corpus for context-dependent semantic parsing. The MRL used for the annotation was designed to support a portable, interactive tourist information system. We develop a semantic parser for this corpus by adapting the imitation learning algorithm DAgger without requiring alignment information during training. DAgger improves upon independently trained classifiers by 9.0 and 4.8 points in F-score on the development and test sets respectively.