S&I Reader: Multi-Granularity Gated Multi-Hop Skimming and Intensive Reading Model for Machine Reading Comprehension

Machine reading comprehension is a very challenging task, which aims to determine the answer span based on the given context and question. The newly developed pre-training language model has achieved a series of successes in various natural language understanding tasks with its powerful contextual r...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yong Wang, Chong Lei, Duoqian Miao
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Gated mechanism granular computing intensive reading machine reading comprehension pre-training model skimming Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/dfa5c9159a3740ec82775456202f875e
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:dfa5c9159a3740ec82775456202f875e
record_format	dspace
spelling	oai:doaj.org-article:dfa5c9159a3740ec82775456202f875e2021-11-19T00:07:04ZS&I Reader: Multi-Granularity Gated Multi-Hop Skimming and Intensive Reading Model for Machine Reading Comprehension2169-353610.1109/ACCESS.2021.3079165https://doaj.org/article/dfa5c9159a3740ec82775456202f875e2021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9427491/https://doaj.org/toc/2169-3536Machine reading comprehension is a very challenging task, which aims to determine the answer span based on the given context and question. The newly developed pre-training language model has achieved a series of successes in various natural language understanding tasks with its powerful contextual representation ability. However, these pre-training language models generally lack the downstream processing structure for specific tasks, which limits further performance improvement. In order to solve this problem and deepen the model’s understanding of the question and context, this paper proposes S&I Reader. On the basis of the pre-training model, skimming, intensive reading, and gated mechanism modules are added to simulate the behavior of humans reading text and filtering information. Based on the idea of granular computing, a multi-granularity module for computing context granularity and sequence granularity is added to the model to simulate the behavior of human beings to understand the text from words to sentences, from parts to the whole. Compared with the previous machine reading comprehension model, our model structure is novel. The skimming module and multi-granularity module proposed in this paper are used to solve the problem that the previous model ignores the key information of the text and cannot understand the text with multi granularity. Experiments show that the model proposed in this paper is effective for both Chinese and English datasets. It can better understand the question and context and give a more accurate answer. The performance has made new progress on the basis of the baseline model.Yong WangChong LeiDuoqian MiaoIEEEarticleGated mechanismgranular computingintensive readingmachine reading comprehensionpre-training modelskimmingElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 75778-75788 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Gated mechanism granular computing intensive reading machine reading comprehension pre-training model skimming Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Gated mechanism granular computing intensive reading machine reading comprehension pre-training model skimming Electrical engineering. Electronics. Nuclear engineering TK1-9971 Yong Wang Chong Lei Duoqian Miao S&I Reader: Multi-Granularity Gated Multi-Hop Skimming and Intensive Reading Model for Machine Reading Comprehension
description	Machine reading comprehension is a very challenging task, which aims to determine the answer span based on the given context and question. The newly developed pre-training language model has achieved a series of successes in various natural language understanding tasks with its powerful contextual representation ability. However, these pre-training language models generally lack the downstream processing structure for specific tasks, which limits further performance improvement. In order to solve this problem and deepen the model’s understanding of the question and context, this paper proposes S&I Reader. On the basis of the pre-training model, skimming, intensive reading, and gated mechanism modules are added to simulate the behavior of humans reading text and filtering information. Based on the idea of granular computing, a multi-granularity module for computing context granularity and sequence granularity is added to the model to simulate the behavior of human beings to understand the text from words to sentences, from parts to the whole. Compared with the previous machine reading comprehension model, our model structure is novel. The skimming module and multi-granularity module proposed in this paper are used to solve the problem that the previous model ignores the key information of the text and cannot understand the text with multi granularity. Experiments show that the model proposed in this paper is effective for both Chinese and English datasets. It can better understand the question and context and give a more accurate answer. The performance has made new progress on the basis of the baseline model.
format	article
author	Yong Wang Chong Lei Duoqian Miao
author_facet	Yong Wang Chong Lei Duoqian Miao
author_sort	Yong Wang
title	S&I Reader: Multi-Granularity Gated Multi-Hop Skimming and Intensive Reading Model for Machine Reading Comprehension
title_short	S&I Reader: Multi-Granularity Gated Multi-Hop Skimming and Intensive Reading Model for Machine Reading Comprehension
title_full	S&I Reader: Multi-Granularity Gated Multi-Hop Skimming and Intensive Reading Model for Machine Reading Comprehension
title_fullStr	S&I Reader: Multi-Granularity Gated Multi-Hop Skimming and Intensive Reading Model for Machine Reading Comprehension
title_full_unstemmed	S&I Reader: Multi-Granularity Gated Multi-Hop Skimming and Intensive Reading Model for Machine Reading Comprehension
title_sort	s&i reader: multi-granularity gated multi-hop skimming and intensive reading model for machine reading comprehension
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/dfa5c9159a3740ec82775456202f875e
work_keys_str_mv	AT yongwang sx0026ireadermultigranularitygatedmultihopskimmingandintensivereadingmodelformachinereadingcomprehension AT chonglei sx0026ireadermultigranularitygatedmultihopskimmingandintensivereadingmodelformachinereadingcomprehension AT duoqianmiao sx0026ireadermultigranularitygatedmultihopskimmingandintensivereadingmodelformachinereadingcomprehension
_version_	1718420640297385984

S&#x0026;I Reader: Multi-Granularity Gated Multi-Hop Skimming and Intensive Reading Model for Machine Reading Comprehension

Ejemplares similares

S&I Reader: Multi-Granularity Gated Multi-Hop Skimming and Intensive Reading Model for Machine Reading Comprehension