@inproceedings{lo-etal-2024-distributional,
title = "Distributional Inclusion Hypothesis and Quantifications: Probing for Hypernymy in Functional Distributional Semantics",
author = "Lo, Chun Hei and
Lam, Wai and
Cheng, Hong and
Emerson, Guy",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.luhme-long.784/",
doi = "10.18653/v1/2024.acl-long.784",
pages = "14625--14637",
abstract = "Functional Distributional Semantics (FDS) models the meaning of words by truth-conditional functions. This provides a natural representation for hypernymy but no guarantee that it can be learnt when FDS models are trained on a corpus. In this paper, we probe into FDS models and study the representations learnt, drawing connections between quantifications, the Distributional Inclusion Hypothesis (DIH), and the variational-autoencoding objective of FDS model training. Using synthetic data sets, we reveal that FDS models learn hypernymy on a restricted class of corpus that strictly follows the DIH. We further introduce a training objective that both enables hypernymy learning under the reverse of the DIH and improves hypernymy detection from real corpora."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lo-etal-2024-distributional">
<titleInfo>
<title>Distributional Inclusion Hypothesis and Quantifications: Probing for Hypernymy in Functional Distributional Semantics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chun</namePart>
<namePart type="given">Hei</namePart>
<namePart type="family">Lo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wai</namePart>
<namePart type="family">Lam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hong</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guy</namePart>
<namePart type="family">Emerson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Functional Distributional Semantics (FDS) models the meaning of words by truth-conditional functions. This provides a natural representation for hypernymy but no guarantee that it can be learnt when FDS models are trained on a corpus. In this paper, we probe into FDS models and study the representations learnt, drawing connections between quantifications, the Distributional Inclusion Hypothesis (DIH), and the variational-autoencoding objective of FDS model training. Using synthetic data sets, we reveal that FDS models learn hypernymy on a restricted class of corpus that strictly follows the DIH. We further introduce a training objective that both enables hypernymy learning under the reverse of the DIH and improves hypernymy detection from real corpora.</abstract>
<identifier type="citekey">lo-etal-2024-distributional</identifier>
<identifier type="doi">10.18653/v1/2024.acl-long.784</identifier>
<location>
<url>https://aclanthology.org/2024.luhme-long.784/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>14625</start>
<end>14637</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Distributional Inclusion Hypothesis and Quantifications: Probing for Hypernymy in Functional Distributional Semantics
%A Lo, Chun Hei
%A Lam, Wai
%A Cheng, Hong
%A Emerson, Guy
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F lo-etal-2024-distributional
%X Functional Distributional Semantics (FDS) models the meaning of words by truth-conditional functions. This provides a natural representation for hypernymy but no guarantee that it can be learnt when FDS models are trained on a corpus. In this paper, we probe into FDS models and study the representations learnt, drawing connections between quantifications, the Distributional Inclusion Hypothesis (DIH), and the variational-autoencoding objective of FDS model training. Using synthetic data sets, we reveal that FDS models learn hypernymy on a restricted class of corpus that strictly follows the DIH. We further introduce a training objective that both enables hypernymy learning under the reverse of the DIH and improves hypernymy detection from real corpora.
%R 10.18653/v1/2024.acl-long.784
%U https://aclanthology.org/2024.luhme-long.784/
%U https://doi.org/10.18653/v1/2024.acl-long.784
%P 14625-14637
Markdown (Informal)
[Distributional Inclusion Hypothesis and Quantifications: Probing for Hypernymy in Functional Distributional Semantics](https://aclanthology.org/2024.luhme-long.784/) (Lo et al., ACL 2024)
ACL