This paper introduces the task of factual error correction: performing edits to a claim so that the generated rewrite is supported by evidence. This serves two purposes: firstly this provides a mechanism to correct written texts that contain misinformation, and secondly, this acts as an inherent explanation for claims already partially supported by evidence. We demonstrate that factual error correction is possible without the need for any additional training data using distant-supervision and retrieved evidence. We release a dataset of 65,000 instances, based on a recent fact verification dataset, to compare our distantly-supervised method to a fully supervised ceiling system. Our manual evaluation indicates which automated evaluation metrics best correlate with human judgements of factuality and whether errors were actually corrected.
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 which we collected via crowdsourcing. 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%.
The biases present in training datasets have been shown to be affecting models for a number of tasks such as natural language inference(NLI) and fact verification. While fine-tuning models on additional data has been used to mitigate such biases, a common issue is that of catastrophic forgetting of the original task. In this paper, we show that elastic weight consolidation (EWC) allows fine-tuning of models to mitigate biases for NLI and fact verification while being less susceptible to catastrophic forgetting. In our evaluation on fact verification systems, we show that fine-tuning with EWC Pareto dominates standard fine-tuning, yielding models lower levels of forgetting on the original task for equivalent gains in accuracy on the fine-tuned task. Additionally, we show that systems trained on NLI can be fine-tuned to improve their accuracy on stress test challenge tasks with minimal loss in accuracy on the MultiNLI dataset despite greater domain shift.
Neural sequence-to-sequence models provide a competitive approach to the task of mapping a question in natural language to an SQL query, also referred to as text-to-SQL generation. The Byte-Pair Encoding algorithm (BPE) has previously been used to improve machine translation (MT) between natural languages. In this work, we adapt BPE for text-to-SQL generation. As the datasets for this task are rather small compared to MT, we present a novel stopping criterion that prevents overfitting the BPE encoding to the training set. Additionally, we present AST BPE, which is a version of BPE that uses the Abstract Syntax Tree (AST) of the SQL statement to guide BPE merges and therefore produce BPE encodings that generalize better. We improved the accuracy of a strong attentive seq2seq baseline on five out of six English text-to-SQL tasks while reducing training time by more than 50% on four of them due to the shortened targets. Finally, on two of these tasks we exceeded previously reported accuracies.
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 exhibiting 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 F1 points 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.
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. %which smoothly groups entities into single vectors across multiple levels. 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.
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.
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.