Aspectuality Across Genre: A Distributional Semantics Approach

Aspectuality Across Genre: A Distributional Semantics Approach

The interpretation of the lexical aspect of verbs in English plays a crucial role for recognizing textual entailment and learning discourse-level inferences. We show that two elementary dimensions of aspectual class, states vs. events, and telic vs. atelic events, can be modelled effectively with di...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2020-10
Hauptverfasser: Kober, Thomas, Alikhani, Malihe, Stone, Matthew, Steedman, Mark
Format: Artikel
Sprache:eng
Schlagworte:
Datasets
Semantics
Words (language)
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 Kober, Thomas
Alikhani, Malihe
Stone, Matthew
Steedman, Mark
description The interpretation of the lexical aspect of verbs in English plays a crucial role for recognizing textual entailment and learning discourse-level inferences. We show that two elementary dimensions of aspectual class, states vs. events, and telic vs. atelic events, can be modelled effectively with distributional semantics. We find that a verb's local context is most indicative of its aspectual class, and demonstrate that closed class words tend to be stronger discriminating contexts than content words. Our approach outperforms previous work on three datasets. Lastly, we contribute a dataset of human--human conversations annotated with lexical aspect and present experiments that show the correlation of telicity with genre and discourse goals.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2457144662</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2457144662</sourcerecordid><originalsourceid>FETCH-proquest_journals_24571446623</originalsourceid><addsrcrecordid>eNqNi70KwjAYAIMgWLTvEHAupF-SVhyE4O-ue4khYkpsar5k8O3t4AM43XB3M1IA53W1EQALUiL2jDFoWpCSF2SncLQmZe1d-lBlYkCkZztEu6WKHhym6O45uTBoT6_2pYfkDFI1jjFo81yR-UN7tOWPS7I-HW_7SzXpd7aYuj7kOL3YgZBtLUTTAP-v-gK0uzhG</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2457144662</pqid></control><display><type>article</type><title>Aspectuality Across Genre: A Distributional Semantics Approach</title><source>Free E- Journals</source><creator>Kober, Thomas ; Alikhani, Malihe ; Stone, Matthew ; Steedman, Mark</creator><creatorcontrib>Kober, Thomas ; Alikhani, Malihe ; Stone, Matthew ; Steedman, Mark</creatorcontrib><description>The interpretation of the lexical aspect of verbs in English plays a crucial role for recognizing textual entailment and learning discourse-level inferences. We show that two elementary dimensions of aspectual class, states vs. events, and telic vs. atelic events, can be modelled effectively with distributional semantics. We find that a verb's local context is most indicative of its aspectual class, and demonstrate that closed class words tend to be stronger discriminating contexts than content words. Our approach outperforms previous work on three datasets. Lastly, we contribute a dataset of human--human conversations annotated with lexical aspect and present experiments that show the correlation of telicity with genre and discourse goals.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Datasets ; Semantics ; Words (language)</subject><ispartof>arXiv.org, 2020-10</ispartof><rights>2020. 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>776,780</link.rule.ids></links><search><creatorcontrib>Kober, Thomas</creatorcontrib><creatorcontrib>Alikhani, Malihe</creatorcontrib><creatorcontrib>Stone, Matthew</creatorcontrib><creatorcontrib>Steedman, Mark</creatorcontrib><title>Aspectuality Across Genre: A Distributional Semantics Approach</title><title>arXiv.org</title><description>The interpretation of the lexical aspect of verbs in English plays a crucial role for recognizing textual entailment and learning discourse-level inferences. We show that two elementary dimensions of aspectual class, states vs. events, and telic vs. atelic events, can be modelled effectively with distributional semantics. We find that a verb's local context is most indicative of its aspectual class, and demonstrate that closed class words tend to be stronger discriminating contexts than content words. Our approach outperforms previous work on three datasets. Lastly, we contribute a dataset of human--human conversations annotated with lexical aspect and present experiments that show the correlation of telicity with genre and discourse goals.</description><subject>Datasets</subject><subject>Semantics</subject><subject>Words (language)</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNqNi70KwjAYAIMgWLTvEHAupF-SVhyE4O-ue4khYkpsar5k8O3t4AM43XB3M1IA53W1EQALUiL2jDFoWpCSF2SncLQmZe1d-lBlYkCkZztEu6WKHhym6O45uTBoT6_2pYfkDFI1jjFo81yR-UN7tOWPS7I-HW_7SzXpd7aYuj7kOL3YgZBtLUTTAP-v-gK0uzhG</recordid><startdate>20201031</startdate><enddate>20201031</enddate><creator>Kober, Thomas</creator><creator>Alikhani, Malihe</creator><creator>Stone, Matthew</creator><creator>Steedman, Mark</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>20201031</creationdate><title>Aspectuality Across Genre: A Distributional Semantics Approach</title><author>Kober, Thomas ; Alikhani, Malihe ; Stone, Matthew ; Steedman, Mark</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_24571446623</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Datasets</topic><topic>Semantics</topic><topic>Words (language)</topic><toplevel>online_resources</toplevel><creatorcontrib>Kober, Thomas</creatorcontrib><creatorcontrib>Alikhani, Malihe</creatorcontrib><creatorcontrib>Stone, Matthew</creatorcontrib><creatorcontrib>Steedman, Mark</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Database (Proquest)</collection><collection>ProQuest Central (Alumni)</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</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</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>Kober, Thomas</au><au>Alikhani, Malihe</au><au>Stone, Matthew</au><au>Steedman, Mark</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Aspectuality Across Genre: A Distributional Semantics Approach</atitle><jtitle>arXiv.org</jtitle><date>2020-10-31</date><risdate>2020</risdate><eissn>2331-8422</eissn><abstract>The interpretation of the lexical aspect of verbs in English plays a crucial role for recognizing textual entailment and learning discourse-level inferences. We show that two elementary dimensions of aspectual class, states vs. events, and telic vs. atelic events, can be modelled effectively with distributional semantics. We find that a verb's local context is most indicative of its aspectual class, and demonstrate that closed class words tend to be stronger discriminating contexts than content words. Our approach outperforms previous work on three datasets. Lastly, we contribute a dataset of human--human conversations annotated with lexical aspect and present experiments that show the correlation of telicity with genre and discourse goals.</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, 2020-10
issn 2331-8422
language eng
recordid cdi_proquest_journals_2457144662
source Free E- Journals
subjects Datasets
Semantics
Words (language)
title Aspectuality Across Genre: A Distributional Semantics Approach
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-01T06%3A58%3A09IST&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=Aspectuality%20Across%20Genre:%20A%20Distributional%20Semantics%20Approach&rft.jtitle=arXiv.org&rft.au=Kober,%20Thomas&rft.date=2020-10-31&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2457144662%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2457144662&rft_id=info:pmid/&rfr_iscdi=true