Extracting Event Temporal Relations via Hyperbolic Geometry

Detecting events and their evolution through time is a crucial task in natural language understanding. Recent neural approaches to event temporal relation extraction typically map events to embeddings in the Euclidean space and train a classifier to detect temporal relations between event pairs. How...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2024-06
Hauptverfasser: Tan, Xingwei, Pergola, Gabriele, He, Yulan
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Tan, Xingwei
Pergola, Gabriele
He, Yulan
description Detecting events and their evolution through time is a crucial task in natural language understanding. Recent neural approaches to event temporal relation extraction typically map events to embeddings in the Euclidean space and train a classifier to detect temporal relations between event pairs. However, embeddings in the Euclidean space cannot capture richer asymmetric relations such as event temporal relations. We thus propose to embed events into hyperbolic spaces, which are intrinsically oriented at modeling hierarchical structures. We introduce two approaches to encode events and their temporal relations in hyperbolic spaces. One approach leverages hyperbolic embeddings to directly infer event relations through simple geometrical operations. In the second one, we devise an end-to-end architecture composed of hyperbolic neural units tailored for the temporal relation extraction task. Thorough experimental assessments on widely used datasets have shown the benefits of revisiting the tasks on a different geometrical space, resulting in state-of-the-art performance on several standard metrics. Finally, the ablation study and several qualitative analyses highlighted the rich event semantics implicitly encoded into hyperbolic spaces.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2572355629</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2572355629</sourcerecordid><originalsourceid>FETCH-proquest_journals_25723556293</originalsourceid><addsrcrecordid>eNqNyrEKwjAUQNEgCBbtPwScC_HFtIqjRDtL9xLLU1LSJCZpsX-vgx_gdIdzFyQDznfFYQ-wInmMPWMMygqE4Bk5yXcKqkvaPqmc0Cba4OBdUIbe0KiknY100orWs8dwd0Z39IpuwBTmDVk-lImY_7om24tsznXhg3uNGFPbuzHYL7UgKuBClHDk_10fItA3iQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2572355629</pqid></control><display><type>article</type><title>Extracting Event Temporal Relations via Hyperbolic Geometry</title><source>Free E- Journals</source><creator>Tan, Xingwei ; Pergola, Gabriele ; He, Yulan</creator><creatorcontrib>Tan, Xingwei ; Pergola, Gabriele ; He, Yulan</creatorcontrib><description>Detecting events and their evolution through time is a crucial task in natural language understanding. Recent neural approaches to event temporal relation extraction typically map events to embeddings in the Euclidean space and train a classifier to detect temporal relations between event pairs. However, embeddings in the Euclidean space cannot capture richer asymmetric relations such as event temporal relations. We thus propose to embed events into hyperbolic spaces, which are intrinsically oriented at modeling hierarchical structures. We introduce two approaches to encode events and their temporal relations in hyperbolic spaces. One approach leverages hyperbolic embeddings to directly infer event relations through simple geometrical operations. In the second one, we devise an end-to-end architecture composed of hyperbolic neural units tailored for the temporal relation extraction task. Thorough experimental assessments on widely used datasets have shown the benefits of revisiting the tasks on a different geometrical space, resulting in state-of-the-art performance on several standard metrics. Finally, the ablation study and several qualitative analyses highlighted the rich event semantics implicitly encoded into hyperbolic spaces.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Ablation ; Euclidean geometry ; Euclidean space ; Qualitative analysis ; Semantics ; Structural hierarchy</subject><ispartof>arXiv.org, 2024-06</ispartof><rights>2024. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>780,784</link.rule.ids></links><search><creatorcontrib>Tan, Xingwei</creatorcontrib><creatorcontrib>Pergola, Gabriele</creatorcontrib><creatorcontrib>He, Yulan</creatorcontrib><title>Extracting Event Temporal Relations via Hyperbolic Geometry</title><title>arXiv.org</title><description>Detecting events and their evolution through time is a crucial task in natural language understanding. Recent neural approaches to event temporal relation extraction typically map events to embeddings in the Euclidean space and train a classifier to detect temporal relations between event pairs. However, embeddings in the Euclidean space cannot capture richer asymmetric relations such as event temporal relations. We thus propose to embed events into hyperbolic spaces, which are intrinsically oriented at modeling hierarchical structures. We introduce two approaches to encode events and their temporal relations in hyperbolic spaces. One approach leverages hyperbolic embeddings to directly infer event relations through simple geometrical operations. In the second one, we devise an end-to-end architecture composed of hyperbolic neural units tailored for the temporal relation extraction task. Thorough experimental assessments on widely used datasets have shown the benefits of revisiting the tasks on a different geometrical space, resulting in state-of-the-art performance on several standard metrics. Finally, the ablation study and several qualitative analyses highlighted the rich event semantics implicitly encoded into hyperbolic spaces.</description><subject>Ablation</subject><subject>Euclidean geometry</subject><subject>Euclidean space</subject><subject>Qualitative analysis</subject><subject>Semantics</subject><subject>Structural hierarchy</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNyrEKwjAUQNEgCBbtPwScC_HFtIqjRDtL9xLLU1LSJCZpsX-vgx_gdIdzFyQDznfFYQ-wInmMPWMMygqE4Bk5yXcKqkvaPqmc0Cba4OBdUIbe0KiknY100orWs8dwd0Z39IpuwBTmDVk-lImY_7om24tsznXhg3uNGFPbuzHYL7UgKuBClHDk_10fItA3iQ</recordid><startdate>20240608</startdate><enddate>20240608</enddate><creator>Tan, Xingwei</creator><creator>Pergola, Gabriele</creator><creator>He, Yulan</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20240608</creationdate><title>Extracting Event Temporal Relations via Hyperbolic Geometry</title><author>Tan, Xingwei ; Pergola, Gabriele ; He, Yulan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_25723556293</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Ablation</topic><topic>Euclidean geometry</topic><topic>Euclidean space</topic><topic>Qualitative analysis</topic><topic>Semantics</topic><topic>Structural hierarchy</topic><toplevel>online_resources</toplevel><creatorcontrib>Tan, Xingwei</creatorcontrib><creatorcontrib>Pergola, Gabriele</creatorcontrib><creatorcontrib>He, Yulan</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Access via ProQuest (Open Access)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Tan, Xingwei</au><au>Pergola, Gabriele</au><au>He, Yulan</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Extracting Event Temporal Relations via Hyperbolic Geometry</atitle><jtitle>arXiv.org</jtitle><date>2024-06-08</date><risdate>2024</risdate><eissn>2331-8422</eissn><abstract>Detecting events and their evolution through time is a crucial task in natural language understanding. Recent neural approaches to event temporal relation extraction typically map events to embeddings in the Euclidean space and train a classifier to detect temporal relations between event pairs. However, embeddings in the Euclidean space cannot capture richer asymmetric relations such as event temporal relations. We thus propose to embed events into hyperbolic spaces, which are intrinsically oriented at modeling hierarchical structures. We introduce two approaches to encode events and their temporal relations in hyperbolic spaces. One approach leverages hyperbolic embeddings to directly infer event relations through simple geometrical operations. In the second one, we devise an end-to-end architecture composed of hyperbolic neural units tailored for the temporal relation extraction task. Thorough experimental assessments on widely used datasets have shown the benefits of revisiting the tasks on a different geometrical space, resulting in state-of-the-art performance on several standard metrics. Finally, the ablation study and several qualitative analyses highlighted the rich event semantics implicitly encoded into hyperbolic spaces.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2024-06
issn 2331-8422
language eng
recordid cdi_proquest_journals_2572355629
source Free E- Journals
subjects Ablation
Euclidean geometry
Euclidean space
Qualitative analysis
Semantics
Structural hierarchy
title Extracting Event Temporal Relations via Hyperbolic Geometry
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-26T02%3A45%3A05IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Extracting%20Event%20Temporal%20Relations%20via%20Hyperbolic%20Geometry&rft.jtitle=arXiv.org&rft.au=Tan,%20Xingwei&rft.date=2024-06-08&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2572355629%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2572355629&rft_id=info:pmid/&rfr_iscdi=true