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.
Fact verification has attracted a lot of attention in the machine learning and natural language processing communities, as it is one of the key methods for detecting misinformation. Existing large-scale benchmarks for this task have focused mostly on textual sources, i.e. unstructured information, and thus ignored the wealth of information available in structured formats, such as tables. In this paper we introduce a novel dataset and benchmark, Fact Extraction and VERification Over Unstructured and Structured information (FEVEROUS), which consists of 87,026 verified claims. Each claim is annotated with evidence in the form of sentences and/or cells from tables in Wikipedia, as well as a label indicating whether this evidence supports, refutes, or does not provide enough information to reach a verdict. Furthermore, we detail our efforts to track and minimize the biases present in the dataset and could be exploited by models, e.g. being able to predict the label without using evidence. Finally, we develop a baseline for verifying claims against text and tables which predicts both the correct evidence and verdict for 18% of the claims.
Claim verification is the task of predicting the veracity of written statements against evidence. Previous large-scale datasets model the task as classification, ignoring the need to retrieve evidence, or are constructed for research purposes, and may not be representative of real-world needs. In this paper, we introduce a novel claim verification dataset with instances derived from search-engine queries, yielding 10,987 claims annotated with evidence that represent real-world information needs. For each claim, we annotate evidence from full Wikipedia articles with both section and sentence-level granularity. Our annotation allows comparison between two complementary approaches to verification: stance classification, and evidence extraction followed by entailment recognition. In our comprehensive evaluation, we find no significant difference in accuracy between these two approaches. This enables systems to use evidence extraction to summarize a rationale for an end-user while maintaining the accuracy when predicting a claim's veracity. With challenging claims and evidence documents containing hundreds of sentences, our dataset presents interesting challenges that are not captured in previous work -- evidenced through transfer learning experiments. We release code and data to support further research on this task.
The regulatory framework of cryptocurrencies (and, in general, blockchain tokens) is of paramount importance. This framework drives nearly all key decisions in the respective business areas. In this work, a computational model is proposed for quantitatively estimating the regulatory stance of countries with respect to cryptocurrencies. This is conducted via web mining utilizing web search engines. The proposed model is experimentally validated. In addition, unsupervised learning (clustering) is applied for better analyzing the automatically derived estimations. Overall, very good performance is achieved by the proposed algorithmic approach.
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.
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.
Disagreements are pervasive in human communication. In this paper we investigate what makes disagreement constructive. To this end, we construct WikiDisputes, a corpus of 7 425 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.
As the blockchain ecosystem gets more mature many businesses, investors, and entrepreneurs are seeking opportunities on working with blockchain systems and cryptocurrencies. A critical challenge for these actors is to identify the most suitable environment to start or evolve their businesses. In general, the question is to identify which countries are offering the most suitable conditions to host their blockchain-based activities and implement their innovative projects. The Blockchain Readiness Index (BRI) provides a numerical metric (referred to as the blockchain readiness score) in measuring the maturity/readiness levels of a country in adopting blockchain and cryptocurrencies. In doing so, BRI leverages on techniques from information retrieval to algorithmically derive an index ranking for a set of countries. The index considers a range of indicators organized under five pillars: Government Regulation, Research, Technology, Industry, and User Engagement. In this paper, we further extent BRI with the capability of deriving the index - at the country level - even in the presence of missing information for the indicators. In doing so, we are proposing two weighting schemes namely, linear and sigmoid weighting for refining the initial estimates for the indicator values. A classification framework was employed to evaluate the effectiveness of the developed techniques which yielded to a significant classification accuracy.