Financial Causality Extraction Based on Universal Dependencies and Clue Expressions
This paper proposes a method to extract financial causal knowledge from bi-lingual text data. Domain-specific causal knowledge plays an important role in human intellectual activities, especially expert decision making. Especially, in the financial area, fund managers, financial analysts, etc. need...
Gespeichert in:
Veröffentlicht in: | New generation computing 2023-11, Vol.41 (4), p.839-857 |
---|---|
Hauptverfasser: | , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 857 |
---|---|
container_issue | 4 |
container_start_page | 839 |
container_title | New generation computing |
container_volume | 41 |
creator | Sakaji, Hiroki Izumi, Kiyoshi |
description | This paper proposes a method to extract financial causal knowledge from bi-lingual text data. Domain-specific causal knowledge plays an important role in human intellectual activities, especially expert decision making. Especially, in the financial area, fund managers, financial analysts, etc. need causal knowledge for their works. Natural language processing is highly effective for extracting human-perceived causality; however, there are two major problems with existing methods. First, causality relative to global activities must be extracted from text data in multiple languages; however, multilingual causality extraction has not been established to date. Second, technologies to extract complex causal structures, e.g., nested causalities, are insufficient. We consider that a model using universal dependencies can extract bi-lingual and nested causalities can be established using clues, e.g., “because” and “since.” Thus, to solve these problems, the proposed model extracts nested causalities based on such clues and universal dependencies in multilingual text data. The proposed financial causality extraction method was evaluated on bi-lingual text data from the financial domain, and the results demonstrated that the proposed model outperformed existing models in the experiment. |
doi_str_mv | 10.1007/s00354-023-00233-2 |
format | Article |
fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2895315007</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2895315007</sourcerecordid><originalsourceid>FETCH-LOGICAL-c314t-7ab19fb62e45428c9932ec33c8c1004c13b23714579586ba32756d16a22b4bcb3</originalsourceid><addsrcrecordid>eNp9kE1PxCAQQInRxPXjD3hq4hmFGWjpUeuummziQfdMKGVNN5VWaI3770Vr4s0LcHhvyDxCLji74owV15ExlIIyQMrSgRQOyIIrBbRgUh6SBQOlKOYoj8lJjLuE5yhgQZ5XrTfetqbLKjNF07XjPlt-jsHYse19dmuia7L02Pj2w4UEZHducL5xSXIxM77Jqm5yyRmCizE58YwcbU0X3fnvfUo2q-VL9UDXT_eP1c2aWuRipIWpebmtc3BCClC2LBGcRbTKpp2E5VgDFlzIopQqrw1CIfOG5wagFrWt8ZRcznOH0L9PLo5610_Bpy81qFIilylNomCmbOhjDG6rh9C-mbDXnOnveHqOp1M3_RNPQ5JwlmKC_asLf6P_sb4A7AVw-w</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2895315007</pqid></control><display><type>article</type><title>Financial Causality Extraction Based on Universal Dependencies and Clue Expressions</title><source>SpringerNature Journals</source><creator>Sakaji, Hiroki ; Izumi, Kiyoshi</creator><creatorcontrib>Sakaji, Hiroki ; Izumi, Kiyoshi</creatorcontrib><description>This paper proposes a method to extract financial causal knowledge from bi-lingual text data. Domain-specific causal knowledge plays an important role in human intellectual activities, especially expert decision making. Especially, in the financial area, fund managers, financial analysts, etc. need causal knowledge for their works. Natural language processing is highly effective for extracting human-perceived causality; however, there are two major problems with existing methods. First, causality relative to global activities must be extracted from text data in multiple languages; however, multilingual causality extraction has not been established to date. Second, technologies to extract complex causal structures, e.g., nested causalities, are insufficient. We consider that a model using universal dependencies can extract bi-lingual and nested causalities can be established using clues, e.g., “because” and “since.” Thus, to solve these problems, the proposed model extracts nested causalities based on such clues and universal dependencies in multilingual text data. The proposed financial causality extraction method was evaluated on bi-lingual text data from the financial domain, and the results demonstrated that the proposed model outperformed existing models in the experiment.</description><identifier>ISSN: 0288-3635</identifier><identifier>EISSN: 1882-7055</identifier><identifier>DOI: 10.1007/s00354-023-00233-2</identifier><language>eng</language><publisher>Tokyo: Springer Japan</publisher><subject>Artificial Intelligence ; Causality ; Computer Hardware ; Computer Science ; Computer Systems Organization and Communication Networks ; Decision analysis ; Multilingualism ; Natural language processing ; Software Engineering/Programming and Operating Systems</subject><ispartof>New generation computing, 2023-11, Vol.41 (4), p.839-857</ispartof><rights>The Author(s) 2023</rights><rights>The Author(s) 2023. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c314t-7ab19fb62e45428c9932ec33c8c1004c13b23714579586ba32756d16a22b4bcb3</cites><orcidid>0000-0001-5030-625X</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s00354-023-00233-2$$EPDF$$P50$$Gspringer$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s00354-023-00233-2$$EHTML$$P50$$Gspringer$$Hfree_for_read</linktohtml><link.rule.ids>314,780,784,27924,27925,41488,42557,51319</link.rule.ids></links><search><creatorcontrib>Sakaji, Hiroki</creatorcontrib><creatorcontrib>Izumi, Kiyoshi</creatorcontrib><title>Financial Causality Extraction Based on Universal Dependencies and Clue Expressions</title><title>New generation computing</title><addtitle>New Gener. Comput</addtitle><description>This paper proposes a method to extract financial causal knowledge from bi-lingual text data. Domain-specific causal knowledge plays an important role in human intellectual activities, especially expert decision making. Especially, in the financial area, fund managers, financial analysts, etc. need causal knowledge for their works. Natural language processing is highly effective for extracting human-perceived causality; however, there are two major problems with existing methods. First, causality relative to global activities must be extracted from text data in multiple languages; however, multilingual causality extraction has not been established to date. Second, technologies to extract complex causal structures, e.g., nested causalities, are insufficient. We consider that a model using universal dependencies can extract bi-lingual and nested causalities can be established using clues, e.g., “because” and “since.” Thus, to solve these problems, the proposed model extracts nested causalities based on such clues and universal dependencies in multilingual text data. The proposed financial causality extraction method was evaluated on bi-lingual text data from the financial domain, and the results demonstrated that the proposed model outperformed existing models in the experiment.</description><subject>Artificial Intelligence</subject><subject>Causality</subject><subject>Computer Hardware</subject><subject>Computer Science</subject><subject>Computer Systems Organization and Communication Networks</subject><subject>Decision analysis</subject><subject>Multilingualism</subject><subject>Natural language processing</subject><subject>Software Engineering/Programming and Operating Systems</subject><issn>0288-3635</issn><issn>1882-7055</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>C6C</sourceid><recordid>eNp9kE1PxCAQQInRxPXjD3hq4hmFGWjpUeuummziQfdMKGVNN5VWaI3770Vr4s0LcHhvyDxCLji74owV15ExlIIyQMrSgRQOyIIrBbRgUh6SBQOlKOYoj8lJjLuE5yhgQZ5XrTfetqbLKjNF07XjPlt-jsHYse19dmuia7L02Pj2w4UEZHducL5xSXIxM77Jqm5yyRmCizE58YwcbU0X3fnvfUo2q-VL9UDXT_eP1c2aWuRipIWpebmtc3BCClC2LBGcRbTKpp2E5VgDFlzIopQqrw1CIfOG5wagFrWt8ZRcznOH0L9PLo5610_Bpy81qFIilylNomCmbOhjDG6rh9C-mbDXnOnveHqOp1M3_RNPQ5JwlmKC_asLf6P_sb4A7AVw-w</recordid><startdate>20231101</startdate><enddate>20231101</enddate><creator>Sakaji, Hiroki</creator><creator>Izumi, Kiyoshi</creator><general>Springer Japan</general><general>Springer Nature B.V</general><scope>C6C</scope><scope>AAYXX</scope><scope>CITATION</scope><orcidid>https://orcid.org/0000-0001-5030-625X</orcidid></search><sort><creationdate>20231101</creationdate><title>Financial Causality Extraction Based on Universal Dependencies and Clue Expressions</title><author>Sakaji, Hiroki ; Izumi, Kiyoshi</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c314t-7ab19fb62e45428c9932ec33c8c1004c13b23714579586ba32756d16a22b4bcb3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Artificial Intelligence</topic><topic>Causality</topic><topic>Computer Hardware</topic><topic>Computer Science</topic><topic>Computer Systems Organization and Communication Networks</topic><topic>Decision analysis</topic><topic>Multilingualism</topic><topic>Natural language processing</topic><topic>Software Engineering/Programming and Operating Systems</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Sakaji, Hiroki</creatorcontrib><creatorcontrib>Izumi, Kiyoshi</creatorcontrib><collection>Springer Nature OA Free Journals</collection><collection>CrossRef</collection><jtitle>New generation computing</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Sakaji, Hiroki</au><au>Izumi, Kiyoshi</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Financial Causality Extraction Based on Universal Dependencies and Clue Expressions</atitle><jtitle>New generation computing</jtitle><stitle>New Gener. Comput</stitle><date>2023-11-01</date><risdate>2023</risdate><volume>41</volume><issue>4</issue><spage>839</spage><epage>857</epage><pages>839-857</pages><issn>0288-3635</issn><eissn>1882-7055</eissn><abstract>This paper proposes a method to extract financial causal knowledge from bi-lingual text data. Domain-specific causal knowledge plays an important role in human intellectual activities, especially expert decision making. Especially, in the financial area, fund managers, financial analysts, etc. need causal knowledge for their works. Natural language processing is highly effective for extracting human-perceived causality; however, there are two major problems with existing methods. First, causality relative to global activities must be extracted from text data in multiple languages; however, multilingual causality extraction has not been established to date. Second, technologies to extract complex causal structures, e.g., nested causalities, are insufficient. We consider that a model using universal dependencies can extract bi-lingual and nested causalities can be established using clues, e.g., “because” and “since.” Thus, to solve these problems, the proposed model extracts nested causalities based on such clues and universal dependencies in multilingual text data. The proposed financial causality extraction method was evaluated on bi-lingual text data from the financial domain, and the results demonstrated that the proposed model outperformed existing models in the experiment.</abstract><cop>Tokyo</cop><pub>Springer Japan</pub><doi>10.1007/s00354-023-00233-2</doi><tpages>19</tpages><orcidid>https://orcid.org/0000-0001-5030-625X</orcidid><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0288-3635 |
ispartof | New generation computing, 2023-11, Vol.41 (4), p.839-857 |
issn | 0288-3635 1882-7055 |
language | eng |
recordid | cdi_proquest_journals_2895315007 |
source | SpringerNature Journals |
subjects | Artificial Intelligence Causality Computer Hardware Computer Science Computer Systems Organization and Communication Networks Decision analysis Multilingualism Natural language processing Software Engineering/Programming and Operating Systems |
title | Financial Causality Extraction Based on Universal Dependencies and Clue Expressions |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T18%3A58%3A54IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Financial%20Causality%20Extraction%20Based%20on%20Universal%20Dependencies%20and%20Clue%20Expressions&rft.jtitle=New%20generation%20computing&rft.au=Sakaji,%20Hiroki&rft.date=2023-11-01&rft.volume=41&rft.issue=4&rft.spage=839&rft.epage=857&rft.pages=839-857&rft.issn=0288-3635&rft.eissn=1882-7055&rft_id=info:doi/10.1007/s00354-023-00233-2&rft_dat=%3Cproquest_cross%3E2895315007%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2895315007&rft_id=info:pmid/&rfr_iscdi=true |