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.

Extracting structured and grounded fact triples from raw text is a fundamental task in Information Extraction (IE). Existing IE datasets are typically collected from Wikipedia articles, using hyperlinks to link entities to the Wikidata knowledge base. However, models trained only on Wikipedia have limitations when applied to web domains, which often contain noisy text or text that does not have any factual information. We present WebIE, the first large-scale, entity-linked closed IE dataset consisting of 1.6M sentences automatically collected from the English Common Crawl corpus. WebIE also includes negative examples, i.e. sentences without fact triples, to better reflect the data on the web. We annotate ~25K triples from WebIE through crowdsourcing and introduce mWebIE, a translation of the annotated set in four other languages: French, Spanish, Portuguese, and Hindi. We evaluate the in-domain, out-of-domain, and zero-shot cross-lingual performance of generative IE models and find models trained on WebIE show better generalisability. We also propose three training strategies that use entity linking as an auxiliary task. Our experiments show that adding Entity-Linking objectives improves the faithfulness of our generative IE models.

End-to-end multilingual entity linking (MEL) is concerned with identifying multilingual entity mentions and their corresponding entity IDs in a knowledge base. Existing works assumed that entity mentions were given and skipped the entity mention detection step due to a lack of high-quality multilingual training corpora. To overcome this limitation, we propose mReFinED, the first end-to-end multilingual entity linking. Additionally, we propose a bootstrapping mention detection framework that enhances the quality of training corpora. Our experimental results demonstrated that mReFinED outperformed the best existing work in the end-to-end MEL task while being 44 times faster.

We introduce ReFinED, an efficient end-to-end entity linking model which uses fine-grained entity types and entity descriptions to perform linking. The model performs mention detection, fine-grained entity typing, and entity disambiguation for all mentions within a document in a single forward pass, making it more than 60 times faster than competitive existing approaches. ReFinED also surpasses state-of-the-art performance on standard entity linking datasets by an average of 3.7 F1. The model is capable of generalising to large-scale knowledge bases such as Wikidata (which has 15 times more entities than Wikipedia) and of zero-shot entity linking. The combination of speed, accuracy and scale makes ReFinED an effective and cost-efficient system for extracting entities from web-scale datasets, for which the model has been successfully deployed.

Relational web-tables are significant sources of structural information that are widely used for relation extraction and population of facts into knowledge graphs. To transform the web-table data into knowledge, we need to identify the relations that exist between column pairs. Currently, there are only a handful of publicly available datasets with relations annotated against natural web-tables. Most datasets are constructed using synthetic tables that lack valuable metadata information, or are limited in size to be considered as a challenging evaluation set. In this paper, we present REDTab, the largest natural-table relation extraction dataset. We have annotated ~9K tables and ~22K column pairs using crowd sourced annotators from MTurk, which has 50x larger number of column pairs than the existing human-annotated benchmark. Our test set is specially designed to be challenging as observed in our experiment results using TaBERT. We publicly release REDTab as a benchmark for the evaluation process in relation extraction.

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.

Automatic unreliable news detection is a research problem with great potential impact. Recently, several papers have shown promising results on large-scale news datasets with models that only use the article itself without resorting to any fact-checking mechanism or retrieving any supporting evidence. In this work, we take a closer look at these datasets. While they all provide valuable resources for future research, we observe a number of problems that may lead to results that do not generalize in more realistic settings. Specifically, we show that selection bias during data collection leads to undesired artifacts in the datasets. In addition, while most systems train and predict at the level of individual articles, overlapping article sources in the training and evaluation data can provide a strong confounding factor that models can exploit. In the presence of this confounding factor, the models can achieve good performance by directly memorizing the site-label mapping instead of modeling the real task of unreliable news detection. We observed a significant drop (>10%) in accuracy for all models tested in a clean split with no train/test source overlap. Using the observations and experimental results, we provide practical suggestions on how to create more reliable datasets for the unreliable news detection task. We suggest future dataset creation include a simple model as a difficulty/bias probe and future model development use a clean non-overlapping site and date split.

It has been shown that knowledge graph embeddings encode potentially harmful social biases, such as the information that women are more likely to be nurses, and men more likely to be bankers. As graph embeddings begin to be used more widely in NLP pipelines, there is a need to develop training methods which remove such biases. Previous approaches to this problem both significantly increase the training time, by a factor of eight or more, and decrease the accuracy of the model substantially. We present a novel approach, in which all embeddings are trained to be neutral to sensitive attributes such as gender by default using an adversarial loss. We then add sensitive attributes back on in whitelisted cases. Training time only marginally increases over a baseline model, and the debiased embeddings perform almost as accurately in the triple prediction task as their non-debiased counterparts.

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.

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.

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.

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.

This paper describes the augmentation of an existing corpus of child-directed speech. The resulting corpus is a gold-standard labeled corpus for supervised learning of semantic role labels in adult-child dialogues. Semantic role labeling (SRL) models assign semantic roles to sentence constituents, thus indicating who has done what to whom (and in what way). The current corpus is derived from the Adam files in the Brown corpus (Brown 1973) of the CHILDES corpora, and augments the partial annotation described in Connor et al. (2010). It provides labels for both semantic arguments of verbs and semantic arguments of prepositions. The semantic role labels and senses of verbs follow Propbank guidelines Kingsbury and Palmer, 2002; Gildea and Palmer 2002; Palmer et al., 2005) and those for prepositions follow Srikumar and Roth (2011). The corpus was annotated by two annotators. Inter-annotator agreement is given separately for prepositions and verbs, and for adult speech and child speech. Overall, across child and adult samples, including verbs and prepositions, the kappa score for sense is 72.6, for the number of semantic-role-bearing arguments, the kappa score is 77.4, for identical semantic role labels on a given argument, the kappa score is 91.1, for the span of semantic role labels, and the kappa for agreement is 93.9. The sense and number of arguments was often open to multiple interpretations in child speech, due to the rapidly changing discourse and omission of constituents in production. Annotators used a discourse context window of ten sentences before and ten sentences after the target utterance to determine the annotation labels. The derived corpus is available for use in CHAT (MacWhinney, 2000) and XML format.

These days, most general knowledge question-answering systems rely on large-scale knowledge bases comprising billions of facts about millions of entities. Having a structured source of semantic knowledge means that we can answer questions involving single static facts (e.g. “Who was the 8th president of the US?”) or dynamically generated ones (e.g. “How old is Donald Trump?”). More importantly, we can answer questions involving multiple inference steps (“Is the queen older than the president of the US?”). In this talk, I’m going to be discussing some of the unique challenges that are involved with building and maintaining a consistent knowledge base for Alexa, extending it with new facts and using it to serve answers in multiple languages. I will focus on three recent projects from our group. First, a way of measuring the completeness of a knowledge base, that is based on usage patterns. The definition of the usage of the KB is done in terms of the relation distribution of entities seen in question-answer logs. Instead of directly estimating the relation distribution of individual entities, it is generalized to the “class signature” of each entity. For example, users ask for baseball players’ height, age, and batting average, so a knowledge base is complete (with respect to baseball players) if every entity has facts for those three relations. Second, an investigation into fact extraction from unstructured text. I will present a method for creating distant (weak) supervision labels for training a large-scale relation extraction system. I will also discuss the effectiveness of neural network approaches by decoupling the model architecture from the feature design of a state-of-the-art neural network system. Surprisingly, a much simpler classifier trained on similar features performs on par with the highly complex neural network system (at 75x reduction to the training time), suggesting that the features are a bigger contributor to the final performance. Finally, I will present the Fact Extraction and VERification (FEVER) dataset and challenge. The dataset comprises more than 185,000 human-generated claims extracted from Wikipedia pages. False claims were generated by mutating true claims in a variety of ways, some of which were meaningaltering. During the verification step, annotators were required to label a claim for its validity and also supply full-sentence textual evidence from (potentially multiple) Wikipedia articles for the label. With FEVER, we aim to help create a new generation of transparent and interprable knowledge extraction systems.

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.

When designing Natural Language Processing (NLP) applications that use Machine Learning (ML) techniques, feature extraction becomes a significant part of the development effort, whether developing a new application or attempting to reproduce results reported for existing NLP tasks. We present EDISON, a Java library of feature generation functions used in a suite of state-of-the-art NLP tools, based on a set of generic NLP data structures. These feature extractors populate simple data structures encoding the extracted features, which the package can also serialize to an intuitive JSON file format that can be easily mapped to formats used by ML packages. EDISON can also be used programmatically with JVM-based (Java/Scala) NLP software to provide the feature extractor input. The collection of feature extractors is organised hierarchically and a simple search interface is provided. In this paper we include examples that demonstrate the versatility and ease-of-use of the EDISON feature extraction suite to show that this can significantly reduce the time spent by developers on feature extraction design for NLP systems. The library is publicly hosted at https://github.com/IllinoisCogComp/illinois-cogcomp-nlp/, and we hope that other NLP researchers will contribute to the set of feature extractors. In this way, the community can help simplify reproduction of published results and the integration of ideas from diverse sources when developing new and improved NLP applications.

Cross document event coreference (CDEC) is an important task that aims at aggregating event-related information across multiple documents. We revisit the evaluation for CDEC, and discover that past works have adopted different, often inconsistent, evaluation settings, which either overlook certain mistakes in coreference decisions, or make assumptions that simplify the coreference task considerably. We suggest a new evaluation methodology which overcomes these limitations, and allows for an accurate assessment of CDEC systems. Our new evaluation setting better reflects the corpus-wide information aggregation ability of CDEC systems by separating event-coreference decisions made across documents from those made within a document. In addition, we suggest a better baseline for the task and semi-automatically identify several inconsistent annotations in the evaluation dataset.

We present a novel way for designing complex joint inference and learning models using Saul (Kordjamshidi et al., 2015), a recently-introduced declarative learning-based programming language (DeLBP). We enrich Saul with components that are necessary for a broad range of learning based Natural Language Processing tasks at various levels of granularity. We illustrate these advances using three different, well-known NLP problems, and show how these generic learning and inference modules can directly exploit Saul’s graph-based data representation. These properties allow the programmer to easily switch between different model formulations and configurations, and consider various kinds of dependencies and correlations among variables of interest with minimal programming effort. We argue that Saul provides an extremely useful paradigm both for the design of advanced NLP systems and for supporting advanced research in NLP.