Deep human answer understanding for natural reverse QA

Article Computer Science, Artificial Intelligence

A Survey on Deep Learning for Named Entity Recognition

Jing Li et al.

Summary: This paper provides a comprehensive review of existing deep learning techniques for named entity recognition (NER), including NER resources, categorization methods, and recent applied techniques. The paper introduces the basics of NER systems and outlines future research directions and challenges in the field.

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

PathReasoner: Explainable reasoning paths for commonsense question answering

Xunlin Zhan et al.

Summary: In this paper, the PathReasoner approach is proposed to explain and facilitate commonsense question answering by explicitly incorporating structured information and external reasoning paths. Experimental results demonstrate the effectiveness of this method, and a case study reveals that reasoning paths provide explainable information for question answering through the PathReasoner.

KNOWLEDGE-BASED SYSTEMS (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

A novel bundling learning paradigm for named entity recognition

Bin Ji et al.

Summary: Multi-task learning (MTL) is a method that leverages the information gained from multiple related natural language processing tasks to improve their performance. In named entity recognition (NER) tasks, traditional MTL-based models often include relation extraction and/or coreference resolution, which require additional data annotations that are usually unavailable in NER corpora. This paper proposes a novel Bundling Learning (BL) paradigm for NER tasks, where sequence labeling-based and span-based NER models are bundled together to model the task from both token- and span-level perspectives. Experimental results demonstrate that BL consistently improves the performance of NER and relation extraction tasks on several benchmark datasets. Detailed analyses further confirm the effectiveness of BL.

KNOWLEDGE-BASED SYSTEMS (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence