Related papers: NumNet: Machine Reading Comprehension with Numeric…

Pruning is a standard technique for removing unnecessary structure from a neural network to reduce its storage footprint, computational demands, or energy consumption. Pruning can reduce the parameter-counts of many state-of-the-art neural…

Numerical Question Answering is the task of answering questions that require numerical capabilities. Previous works introduce general adversarial attacks to Numerical Question Answering, while not systematically exploring numerical…

The problem of relevance ranking consists of sorting a set of objects with respect to a given criterion. Since users may prefer different relevance criteria, the ranking algorithms should be adaptable to the user needs. Two main approaches…

Machine reading comprehension with unanswerable questions is a new challenging task for natural language processing. A key subtask is to reliably predict whether the question is unanswerable. In this paper, we propose a unified model,…

Recent studies report that many machine reading comprehension (MRC) models can perform closely to or even better than humans on benchmark datasets. However, existing works indicate that many MRC models may learn shortcuts to outwit these…

Existing generative pre-trained language models (e.g., GPT) focus on modeling the language structure and semantics of general texts. However, those models do not consider the numerical properties of numbers and cannot perform robustly on…

Neural networks for computer vision extract uninterpretable features despite achieving high accuracy on benchmarks. In contrast, humans can explain their predictions using succinct and intuitive descriptions. To incorporate explainability…

Neural metrics for machine translation evaluation, such as COMET, exhibit significant improvements in their correlation with human judgments, as compared to traditional metrics based on lexical overlap, such as BLEU. Yet, neural metrics…

Reasoning machine reading comprehension (R-MRC) aims to answer complex questions that require discrete reasoning based on text. To support discrete reasoning, evidence, typically the concise textual fragments that describe question-related…

Interactive machine reading comprehension (iMRC) is machine comprehension tasks where knowledge sources are partially observable. An agent must interact with an environment sequentially to gather necessary knowledge in order to answer a…

New findings in natural language processing (NLP) demonstrate that the strong memorization capability contributes a lot to the success of Large Language Models (LLM). This inspires us to explicitly bring an independent memory mechanism into…

Deep learning has proven itself as a successful set of models for learning useful semantic representations of data. These, however, are mostly implicitly learned as part of a classification task. In this paper we propose the triplet network…

Machine comprehension of text is an important problem in natural language processing. A recently released dataset, the Stanford Question Answering Dataset (SQuAD), offers a large number of real questions and their answers created by humans…

Numerical reasoning over hybrid data containing tables and long texts has recently received research attention from the AI community. To generate an executable reasoning program consisting of math and table operations to answer a question,…

Whether neural networks can learn abstract reasoning or whether they merely rely on superficial statistics is a topic of recent debate. Here, we propose a dataset and challenge designed to probe abstract reasoning, inspired by a well-known…

Document-level relation extraction (DocRE) models generally use graph networks to implicitly model the reasoning skill (i.e., pattern recognition, logical reasoning, coreference reasoning, etc.) related to the relation between one entity…

Pre-trained Language Models (PLMs) have achieved great success on Machine Reading Comprehension (MRC) over the past few years. Although the general language representation learned from large-scale corpora does benefit MRC, the poor support…

Understanding charts requires models to jointly reason over geometric visual patterns, structured numerical data, and natural language -- a capability where current vision-language models (VLMs) remain limited. We introduce ChartNet, a…

Although existing machine reading comprehension models are making rapid progress on many datasets, they are far from robust. In this paper, we propose an understanding-oriented machine reading comprehension model to address three kinds of…

Sequence modeling has demonstrated state-of-the-art performance on natural language and document understanding tasks. However, it is challenging to correctly serialize tokens in form-like documents in practice due to their variety of layout…