activity
20182022
most citedDocument-Level Relation Extraction with Reconstruction

7 citations · 33 across the 19 of their papers we have counts for

collaborators

28 papers

cs.CL20222 cited

MuGER: Multi-Granularity Evidence Retrieval and Reasoning for Hybrid Question Answering

Yingyao Wang, Junwei Bao, Chaoqun Duan +3

Hybrid question answering (HQA) aims to answer questions over heterogeneous data, including tables and passages linked to table cells. The heterogeneous data can provide different…

cs.CL2022

UniRPG: Unified Discrete Reasoning over Table and Text as Program Generation

Yongwei Zhou, Junwei Bao, Chaoqun Duan +3

Question answering requiring discrete reasoning, e.g., arithmetic computing, comparison, and counting, over knowledge is a challenging task. In this paper, we propose UniRPG, a sem…

cs.CL20221 cited

Disentangling Reasoning Capabilities from Language Models with Compositional Reasoning Transformers

Wanjun Zhong, Tingting Ma, Jiahai Wang +4

This paper presents ReasonFormer, a unified reasoning framework for mirroring the modular and compositional reasoning process of humans in complex decision-making. Inspired by dual…

cs.CL2022

OPERA:Operation-Pivoted Discrete Reasoning over Text

Yongwei Zhou, Junwei Bao, Chaoqun Duan +7

Machine reading comprehension (MRC) that requires discrete reasoning involving symbolic operations, e.g., addition, sorting, and counting, is a challenging task. According to this…

cs.CL20221 cited

Document-Level Relation Extraction with Sentences Importance Estimation and Focusing

Wang Xu, Kehai Chen, Lili Mou +1

Document-level relation extraction (DocRE) aims to determine the relation between two entities from a document of multiple sentences. Recent studies typically represent the entire…

cs.CL2022

Decomposed Meta-Learning for Few-Shot Named Entity Recognition

Tingting Ma, Huiqiang Jiang, Qianhui Wu +2

Few-shot named entity recognition (NER) systems aim at recognizing novel-class named entities based on only a few labeled examples. In this paper, we present a decomposed meta-lear…