相关论文: Extract, Integrate, Compete: Towards Verification …

Recently, language representation techniques have achieved great performances in text classification. However, most existing representation models are specifically designed for English materials, which may fail in Chinese because of the…

Visual information extraction (VIE) has attracted considerable attention recently owing to its various advanced applications such as document understanding, automatic marking and intelligent education. Most existing works decoupled this…

Although Vietnamese is the 17th most popular native-speaker language in the world, there are not many research studies on Vietnamese machine reading comprehension (MRC), the task of understanding a text and answering questions about it. One…

Several large cloze-style context-question-answer datasets have been introduced recently: the CNN and Daily Mail news data and the Children's Book Test. Thanks to the size of these datasets, the associated text comprehension task is well…

Despite that current reading comprehension systems have achieved significant advancements, their promising performances are often obtained at the cost of making an ensemble of numerous models. Besides, existing approaches are also…

Interpreting the predictions of existing Question Answering (QA) models is critical to many real-world intelligent applications, such as QA systems for healthcare, education, and finance. However, existing QA models lack interpretability…

Visual question answering requires a system to provide an accurate natural language answer given an image and a natural language question. However, it is widely recognized that previous generic VQA methods often exhibit a tendency to…

In this paper, we introduce Spotlight, a novel paradigm for information extraction that produces concise, engaging narratives by highlighting the most compelling aspects of a document. Unlike traditional summaries, which prioritize…

Researchers produce thousands of scholarly documents containing valuable technical knowledge. The community faces the laborious task of reading these documents to identify, extract, and synthesize information. To automate information…

The rapid advancement of information and communication technology has facilitated easier access to information. However, this progress has also necessitated more stringent verification measures to ensure the accuracy of information,…

Deploying machine learning models in resource-constrained environments, such as edge devices or rapid prototyping scenarios, increasingly demands distillation of large datasets into significantly smaller yet informative synthetic datasets.…

Despite rapid progress in claim verification, we lack a systematic understanding of what reasoning these benchmarks actually exercise. We generate structured reasoning traces for 24K claim-verification examples across 9 datasets using…

Chinese Spelling Correction (CSC) aims to detect and correct spelling errors in Chinese sentences caused by phonetic or visual similarities. While current CSC models integrate pinyin or glyph features and have shown significant…

Chinese Grammatical Error Correction (CGEC) has been attracting growing attention from researchers recently. In spite of the fact that multiple CGEC datasets have been developed to support the research, these datasets lack the ability to…

End-to-end neural models have made significant progress in question answering, however recent studies show that these models implicitly assume that the answer and evidence appear close together in a single document. In this work, we propose…

Cloze-style queries are representative problems in reading comprehension. Over the past few months, we have seen much progress that utilizing neural network approach to solve Cloze-style questions. In this paper, we present a novel model…

Question answering (QA) models are well-known to exploit data bias, e.g., the language prior in visual QA and the position bias in reading comprehension. Recent debiasing methods achieve good out-of-distribution (OOD) generalizability with…

Unsupervised pre-training on millions of digital-born or scanned documents has shown promising advances in visual document understanding~(VDU). While various vision-language pre-training objectives are studied in existing solutions, the…

One of the key limitations of traditional machine learning methods is their requirement for training data that exemplifies all the information to be learned. This is a particular problem for visual question answering methods, which may be…

Chinese Spelling Check (CSC) is a task to detect and correct spelling errors in Chinese natural language. Existing methods have made attempts to incorporate the similarity knowledge between Chinese characters. However, they take the…