In the field of natural language processing (NLP), word-embedding-based models have
been widely applied in many tasks with great success, which are believed to make …

This paper investigates various Transformer architectures on the WikiReading Information
Extraction and Machine Reading Comprehension dataset. The proposed dual-source model …

Feature representation and feature extraction are two crucial procedures in text mining.
Convolutional Neural Networks (CNN) have shown overwhelming success for text-mining …

End-to-end question answering (QA) requires both information retrieval (IR) over a large
document collection and machine reading comprehension (MRC) on the retrieved …

We address the challenging problem of Natural Language Comprehension beyond plain-
text documents by introducing the TILT neural network architecture which simultaneously …

Document images are ubiquitous, but existing methods mainly focus on the text reading but
not information understanding. In this paper, we propose a novel document image …

Major scandals in corporate history have urged the need for regulatory compliance, where
organizations need to ensure that their controls (processes) comply with relevant laws …

We publish a Chinese Resume Corpus for researches of information extraction. The corpus
contains 178 thousand resume documents and over 33 million words. The resume …

Low-quality data can cause downstream problems in high-stakes applications. Data-centric
approach emphasizes on improving dataset quality to enhance model performance. High …

Deep language models learning a hierarchical representation proved to be a powerful tool
for natural language processing, text mining and information retrieval. However …