Cargando…

A Cognitive Method for Automatically Retrieving Complex Information on a Large Scale

Modern retrieval systems tend to deteriorate because of their large output of useless and even misleading information, especially for complex search requests on a large scale. Complex information retrieval (IR) tasks requiring multi-hop reasoning need to fuse multiple scattered text across two or mo...

Descripción completa

Detalles Bibliográficos
Autores principales: Wang, Yongyue, Yao, Beitong, Wang, Tianbo, Xia, Chunhe, Zhao, Xianghui
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7308866/
https://www.ncbi.nlm.nih.gov/pubmed/32481652
http://dx.doi.org/10.3390/s20113057
_version_ 1783549090874785792
author Wang, Yongyue
Yao, Beitong
Wang, Tianbo
Xia, Chunhe
Zhao, Xianghui
author_facet Wang, Yongyue
Yao, Beitong
Wang, Tianbo
Xia, Chunhe
Zhao, Xianghui
author_sort Wang, Yongyue
collection PubMed
description Modern retrieval systems tend to deteriorate because of their large output of useless and even misleading information, especially for complex search requests on a large scale. Complex information retrieval (IR) tasks requiring multi-hop reasoning need to fuse multiple scattered text across two or more documents. However, there are two challenges for multi-hop retrieval. To be specific, the first challenge is that since some important supporting facts have little lexical or semantic relationship with the retrieval query, the retriever often omits them; the second challenge is that once a retriever chooses misinformation related to the query as the entities of cognitive graphs, the retriever will fail. In this study, in order to improve the performance of retrievers in complex tasks, an intelligent sensor technique was proposed based on a sub-scope with cognitive reasoning (2SCR-IR), a novel method of retrieving reasoning paths over the cognitive graph to provide users with verified multi-hop reasoning chains. Inspired by the users’ process of step-by-step searching online, 2SCR-IR includes a dynamic fusion layer that starts from the entities mentioned in the given query, explores the cognitive graph dynamically built from the query and contexts, gradually finds relevant supporting entities mentioned in the given documents, and verifies the rationality of the retrieval facts. Our experimental results show that 2SCR-IR achieves competitive results on the HotpotQA full wiki and distractor settings, and outperforms the previous state-of-the-art methods by a more than two points absolute gain on the full wiki setting.
format Online
Article
Text
id pubmed-7308866
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-73088662020-06-25 A Cognitive Method for Automatically Retrieving Complex Information on a Large Scale Wang, Yongyue Yao, Beitong Wang, Tianbo Xia, Chunhe Zhao, Xianghui Sensors (Basel) Article Modern retrieval systems tend to deteriorate because of their large output of useless and even misleading information, especially for complex search requests on a large scale. Complex information retrieval (IR) tasks requiring multi-hop reasoning need to fuse multiple scattered text across two or more documents. However, there are two challenges for multi-hop retrieval. To be specific, the first challenge is that since some important supporting facts have little lexical or semantic relationship with the retrieval query, the retriever often omits them; the second challenge is that once a retriever chooses misinformation related to the query as the entities of cognitive graphs, the retriever will fail. In this study, in order to improve the performance of retrievers in complex tasks, an intelligent sensor technique was proposed based on a sub-scope with cognitive reasoning (2SCR-IR), a novel method of retrieving reasoning paths over the cognitive graph to provide users with verified multi-hop reasoning chains. Inspired by the users’ process of step-by-step searching online, 2SCR-IR includes a dynamic fusion layer that starts from the entities mentioned in the given query, explores the cognitive graph dynamically built from the query and contexts, gradually finds relevant supporting entities mentioned in the given documents, and verifies the rationality of the retrieval facts. Our experimental results show that 2SCR-IR achieves competitive results on the HotpotQA full wiki and distractor settings, and outperforms the previous state-of-the-art methods by a more than two points absolute gain on the full wiki setting. MDPI 2020-05-28 /pmc/articles/PMC7308866/ /pubmed/32481652 http://dx.doi.org/10.3390/s20113057 Text en © 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Wang, Yongyue
Yao, Beitong
Wang, Tianbo
Xia, Chunhe
Zhao, Xianghui
A Cognitive Method for Automatically Retrieving Complex Information on a Large Scale
title A Cognitive Method for Automatically Retrieving Complex Information on a Large Scale
title_full A Cognitive Method for Automatically Retrieving Complex Information on a Large Scale
title_fullStr A Cognitive Method for Automatically Retrieving Complex Information on a Large Scale
title_full_unstemmed A Cognitive Method for Automatically Retrieving Complex Information on a Large Scale
title_short A Cognitive Method for Automatically Retrieving Complex Information on a Large Scale
title_sort cognitive method for automatically retrieving complex information on a large scale
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7308866/
https://www.ncbi.nlm.nih.gov/pubmed/32481652
http://dx.doi.org/10.3390/s20113057
work_keys_str_mv AT wangyongyue acognitivemethodforautomaticallyretrievingcomplexinformationonalargescale
AT yaobeitong acognitivemethodforautomaticallyretrievingcomplexinformationonalargescale
AT wangtianbo acognitivemethodforautomaticallyretrievingcomplexinformationonalargescale
AT xiachunhe acognitivemethodforautomaticallyretrievingcomplexinformationonalargescale
AT zhaoxianghui acognitivemethodforautomaticallyretrievingcomplexinformationonalargescale
AT wangyongyue cognitivemethodforautomaticallyretrievingcomplexinformationonalargescale
AT yaobeitong cognitivemethodforautomaticallyretrievingcomplexinformationonalargescale
AT wangtianbo cognitivemethodforautomaticallyretrievingcomplexinformationonalargescale
AT xiachunhe cognitivemethodforautomaticallyretrievingcomplexinformationonalargescale
AT zhaoxianghui cognitivemethodforautomaticallyretrievingcomplexinformationonalargescale