No Cover Image

Journal article 160 views

Incremental Composition in Distributional Semantics

Matthew Purver Orcid Logo, Mehrnoosh Sadrzadeh Orcid Logo, Ruth Kempson Orcid Logo, Gijs Wijnholds, Julian Hough

Journal of Logic, Language and Information, Volume: 30, Issue: 2, Pages: 379 - 406

Swansea University Author: Julian Hough

Full text not available from this repository: check for access using links below.

Abstract

Despite the incremental nature of Dynamic Syntax (DS), the semantic grounding of it remains that of predicate logic, itself grounded in set theory, so is poorly suited to expressing the rampantly context-relative nature of word meaning, and related phenomena such as incremental judgements of similar...

Full description

Published in: Journal of Logic, Language and Information
ISSN: 0925-8531 1572-9583
Published: Springer Science and Business Media LLC 2021
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa64926
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2023-11-07T20:05:30Z
last_indexed 2023-11-07T20:05:30Z
id cronfa64926
recordtype SURis
fullrecord <?xml version="1.0" encoding="utf-8"?><rfc1807 xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema"><bib-version>v2</bib-version><id>64926</id><entry>2023-11-07</entry><title>Incremental Composition in Distributional Semantics</title><swanseaauthors><author><sid>082d773ae261d2bbf49434dd2608ab40</sid><firstname>Julian</firstname><surname>Hough</surname><name>Julian Hough</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2023-11-07</date><deptcode>SCS</deptcode><abstract>Despite the incremental nature of Dynamic Syntax (DS), the semantic grounding of it remains that of predicate logic, itself grounded in set theory, so is poorly suited to expressing the rampantly context-relative nature of word meaning, and related phenomena such as incremental judgements of similarity needed for the modelling of disambiguation. Here, we show how DS can be assigned a compositional distributional semantics which enables such judgements and makes it possible to incrementally disambiguate language constructs using vector space semantics. Building on a proposal in our previous work, we implement and evaluate our model on real data, showing that it outperforms a commonly used additive baseline. In conclusion, we argue that these results set the ground for an account of the non-determinism of lexical content, in which the nature of word meaning is its dependence on surrounding context for its construal.</abstract><type>Journal Article</type><journal>Journal of Logic, Language and Information</journal><volume>30</volume><journalNumber>2</journalNumber><paginationStart>379</paginationStart><paginationEnd>406</paginationEnd><publisher>Springer Science and Business Media LLC</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>0925-8531</issnPrint><issnElectronic>1572-9583</issnElectronic><keywords/><publishedDay>1</publishedDay><publishedMonth>6</publishedMonth><publishedYear>2021</publishedYear><publishedDate>2021-06-01</publishedDate><doi>10.1007/s10849-021-09337-8</doi><url>http://dx.doi.org/10.1007/s10849-021-09337-8</url><notes/><college>COLLEGE NANME</college><department>Computer Science</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>SCS</DepartmentCode><institution>Swansea University</institution><apcterm>Another institution paid the OA fee</apcterm><funders/><projectreference/><lastEdited>2023-12-21T16:46:49.8865526</lastEdited><Created>2023-11-07T20:00:57.6041967</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>Matthew</firstname><surname>Purver</surname><orcid>0000-0003-2297-1273</orcid><order>1</order></author><author><firstname>Mehrnoosh</firstname><surname>Sadrzadeh</surname><orcid>0000-0002-5863-7835</orcid><order>2</order></author><author><firstname>Ruth</firstname><surname>Kempson</surname><orcid>0000-0002-5096-3812</orcid><order>3</order></author><author><firstname>Gijs</firstname><surname>Wijnholds</surname><order>4</order></author><author><firstname>Julian</firstname><surname>Hough</surname><order>5</order></author></authors><documents/><OutputDurs/></rfc1807>
spelling v2 64926 2023-11-07 Incremental Composition in Distributional Semantics 082d773ae261d2bbf49434dd2608ab40 Julian Hough Julian Hough true false 2023-11-07 SCS Despite the incremental nature of Dynamic Syntax (DS), the semantic grounding of it remains that of predicate logic, itself grounded in set theory, so is poorly suited to expressing the rampantly context-relative nature of word meaning, and related phenomena such as incremental judgements of similarity needed for the modelling of disambiguation. Here, we show how DS can be assigned a compositional distributional semantics which enables such judgements and makes it possible to incrementally disambiguate language constructs using vector space semantics. Building on a proposal in our previous work, we implement and evaluate our model on real data, showing that it outperforms a commonly used additive baseline. In conclusion, we argue that these results set the ground for an account of the non-determinism of lexical content, in which the nature of word meaning is its dependence on surrounding context for its construal. Journal Article Journal of Logic, Language and Information 30 2 379 406 Springer Science and Business Media LLC 0925-8531 1572-9583 1 6 2021 2021-06-01 10.1007/s10849-021-09337-8 http://dx.doi.org/10.1007/s10849-021-09337-8 COLLEGE NANME Computer Science COLLEGE CODE SCS Swansea University Another institution paid the OA fee 2023-12-21T16:46:49.8865526 2023-11-07T20:00:57.6041967 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Matthew Purver 0000-0003-2297-1273 1 Mehrnoosh Sadrzadeh 0000-0002-5863-7835 2 Ruth Kempson 0000-0002-5096-3812 3 Gijs Wijnholds 4 Julian Hough 5
title Incremental Composition in Distributional Semantics
spellingShingle Incremental Composition in Distributional Semantics
Julian Hough
title_short Incremental Composition in Distributional Semantics
title_full Incremental Composition in Distributional Semantics
title_fullStr Incremental Composition in Distributional Semantics
title_full_unstemmed Incremental Composition in Distributional Semantics
title_sort Incremental Composition in Distributional Semantics
author_id_str_mv 082d773ae261d2bbf49434dd2608ab40
author_id_fullname_str_mv 082d773ae261d2bbf49434dd2608ab40_***_Julian Hough
author Julian Hough
author2 Matthew Purver
Mehrnoosh Sadrzadeh
Ruth Kempson
Gijs Wijnholds
Julian Hough
format Journal article
container_title Journal of Logic, Language and Information
container_volume 30
container_issue 2
container_start_page 379
publishDate 2021
institution Swansea University
issn 0925-8531
1572-9583
doi_str_mv 10.1007/s10849-021-09337-8
publisher Springer Science and Business Media LLC
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
url http://dx.doi.org/10.1007/s10849-021-09337-8
document_store_str 0
active_str 0
description Despite the incremental nature of Dynamic Syntax (DS), the semantic grounding of it remains that of predicate logic, itself grounded in set theory, so is poorly suited to expressing the rampantly context-relative nature of word meaning, and related phenomena such as incremental judgements of similarity needed for the modelling of disambiguation. Here, we show how DS can be assigned a compositional distributional semantics which enables such judgements and makes it possible to incrementally disambiguate language constructs using vector space semantics. Building on a proposal in our previous work, we implement and evaluate our model on real data, showing that it outperforms a commonly used additive baseline. In conclusion, we argue that these results set the ground for an account of the non-determinism of lexical content, in which the nature of word meaning is its dependence on surrounding context for its construal.
published_date 2021-06-01T16:46:50Z
_version_ 1785910746481164288
score 11.016235