The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
다중 홉 추론을 사용하는 기계 독해는 항상 세계 지식 부족으로 인해 추론 경로 깨짐으로 인해 항상 오답 감지가 발생합니다. 본 논문에서는 종속관계, 상식 등 이전 연구에서 부족한 지식이 무엇인지 분석한다. 우리의 분석을 바탕으로 우리는 다음을 제안합니다. M다차원 K지식 강화 Graph NMKGN이라는 etwork는 특정 지식을 활용하여 추론 과정의 지식 격차를 해소합니다. 구체적으로, 우리의 접근 방식은 다양한 그래프 신경망을 통한 엔터티 및 종속 관계뿐만 아니라 질문과 맥락 모두의 표현을 향상시키는 것을 목표로 하는 양방향 주의 메커니즘을 통한 상식적 지식도 통합합니다. 또한, 다차원 지식을 최대한 활용하기 위해 두 가지 종류의 융합 아키텍처를 연구합니다. 잇달아 일어나는 및 병렬 방법. HotpotQA 데이터 세트에 대한 실험 결과는 우리 접근 방식의 효율성을 보여 주며 다차원 지식, 특히 종속 관계 및 상식을 사용하면 실제로 추론 프로세스를 개선하고 정답 탐지에 기여할 수 있음을 확인합니다.
Ying ZHANG
Beijing Jiaotong University
Fandong MENG
Tecent Inc
Jinchao ZHANG
Tecent Inc
Yufeng CHEN
Beijing Jiaotong University
Jinan XU
Beijing Jiaotong University
Jie ZHOU
Tecent Inc
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
부
Ying ZHANG, Fandong MENG, Jinchao ZHANG, Yufeng CHEN, Jinan XU, Jie ZHOU, "MKGN: A Multi-Dimensional Knowledge Enhanced Graph Network for Multi-Hop Question and Answering" in IEICE TRANSACTIONS on Information,
vol. E105-D, no. 4, pp. 807-819, April 2022, doi: 10.1587/transinf.2021EDP7154.
Abstract: Machine reading comprehension with multi-hop reasoning always suffers from reasoning path breaking due to the lack of world knowledge, which always results in wrong answer detection. In this paper, we analyze what knowledge the previous work lacks, e.g., dependency relations and commonsense. Based on our analysis, we propose a Multi-dimensional Knowledge enhanced Graph Network, named MKGN, which exploits specific knowledge to repair the knowledge gap in reasoning process. Specifically, our approach incorporates not only entities and dependency relations through various graph neural networks, but also commonsense knowledge by a bidirectional attention mechanism, which aims to enhance representations of both question and contexts. Besides, to make the most of multi-dimensional knowledge, we investigate two kinds of fusion architectures, i.e., in the sequential and parallel manner. Experimental results on HotpotQA dataset demonstrate the effectiveness of our approach and verify that using multi-dimensional knowledge, especially dependency relations and commonsense, can indeed improve the reasoning process and contribute to correct answer detection.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2021EDP7154/_p
부
@ARTICLE{e105-d_4_807,
author={Ying ZHANG, Fandong MENG, Jinchao ZHANG, Yufeng CHEN, Jinan XU, Jie ZHOU, },
journal={IEICE TRANSACTIONS on Information},
title={MKGN: A Multi-Dimensional Knowledge Enhanced Graph Network for Multi-Hop Question and Answering},
year={2022},
volume={E105-D},
number={4},
pages={807-819},
abstract={Machine reading comprehension with multi-hop reasoning always suffers from reasoning path breaking due to the lack of world knowledge, which always results in wrong answer detection. In this paper, we analyze what knowledge the previous work lacks, e.g., dependency relations and commonsense. Based on our analysis, we propose a Multi-dimensional Knowledge enhanced Graph Network, named MKGN, which exploits specific knowledge to repair the knowledge gap in reasoning process. Specifically, our approach incorporates not only entities and dependency relations through various graph neural networks, but also commonsense knowledge by a bidirectional attention mechanism, which aims to enhance representations of both question and contexts. Besides, to make the most of multi-dimensional knowledge, we investigate two kinds of fusion architectures, i.e., in the sequential and parallel manner. Experimental results on HotpotQA dataset demonstrate the effectiveness of our approach and verify that using multi-dimensional knowledge, especially dependency relations and commonsense, can indeed improve the reasoning process and contribute to correct answer detection.},
keywords={},
doi={10.1587/transinf.2021EDP7154},
ISSN={1745-1361},
month={April},}
부
TY - JOUR
TI - MKGN: A Multi-Dimensional Knowledge Enhanced Graph Network for Multi-Hop Question and Answering
T2 - IEICE TRANSACTIONS on Information
SP - 807
EP - 819
AU - Ying ZHANG
AU - Fandong MENG
AU - Jinchao ZHANG
AU - Yufeng CHEN
AU - Jinan XU
AU - Jie ZHOU
PY - 2022
DO - 10.1587/transinf.2021EDP7154
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E105-D
IS - 4
JA - IEICE TRANSACTIONS on Information
Y1 - April 2022
AB - Machine reading comprehension with multi-hop reasoning always suffers from reasoning path breaking due to the lack of world knowledge, which always results in wrong answer detection. In this paper, we analyze what knowledge the previous work lacks, e.g., dependency relations and commonsense. Based on our analysis, we propose a Multi-dimensional Knowledge enhanced Graph Network, named MKGN, which exploits specific knowledge to repair the knowledge gap in reasoning process. Specifically, our approach incorporates not only entities and dependency relations through various graph neural networks, but also commonsense knowledge by a bidirectional attention mechanism, which aims to enhance representations of both question and contexts. Besides, to make the most of multi-dimensional knowledge, we investigate two kinds of fusion architectures, i.e., in the sequential and parallel manner. Experimental results on HotpotQA dataset demonstrate the effectiveness of our approach and verify that using multi-dimensional knowledge, especially dependency relations and commonsense, can indeed improve the reasoning process and contribute to correct answer detection.
ER -