@inproceedings{ruppik-etal-2024-local,
title = "Local Topology Measures of Contextual Language Model Latent Spaces with Applications to Dialogue Term Extraction",
author = "Ruppik, Benjamin Matthias and
Heck, Michael and
van Niekerk, Carel and
Vukovic, Renato and
Lin, Hsien-chin and
Feng, Shutong and
Zibrowius, Marcus and
Gasic, Milica",
editor = "Kawahara, Tatsuya and
Demberg, Vera and
Ultes, Stefan and
Inoue, Koji and
Mehri, Shikib and
Howcroft, David and
Komatani, Kazunori",
booktitle = "Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue",
month = sep,
year = "2024",
address = "Kyoto, Japan",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.sigdial-1.31",
pages = "344--356",
abstract = "A common approach for sequence tagging tasks based on contextual word representations is to train a machine learning classifier directly on these embedding vectors. This approach has two shortcomings. First, such methods consider single input sequences in isolation and are unable to put an individual embedding vector in relation to vectors outside the current local context of use. Second, the high performance of these models relies on fine-tuning the embedding model in conjunction with the classifier, which may not always be feasible due to the size or inaccessibility of the underlying feature-generation model. It is thus desirable, given a collection of embedding vectors of a corpus, i.e. a datastore, to find features of each vector that describe its relation to other, similar vectors in the datastore. With this in mind, we introduce complexity measures of the local topology of the latent space of a contextual language model with respect to a given datastore. The effectiveness of our features is demonstrated through their application to dialogue term extraction. Our work continues a line of research that explores the manifold hypothesis for word embeddings, demonstrating that local structure in the space carved out by word embeddings can be exploited to infer semantic properties.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ruppik-etal-2024-local">
<titleInfo>
<title>Local Topology Measures of Contextual Language Model Latent Spaces with Applications to Dialogue Term Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="given">Matthias</namePart>
<namePart type="family">Ruppik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Heck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carel</namePart>
<namePart type="family">van Niekerk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Renato</namePart>
<namePart type="family">Vukovic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsien-chin</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shutong</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcus</namePart>
<namePart type="family">Zibrowius</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Milica</namePart>
<namePart type="family">Gasic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tatsuya</namePart>
<namePart type="family">Kawahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Ultes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Koji</namePart>
<namePart type="family">Inoue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shikib</namePart>
<namePart type="family">Mehri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Howcroft</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kazunori</namePart>
<namePart type="family">Komatani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Kyoto, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>A common approach for sequence tagging tasks based on contextual word representations is to train a machine learning classifier directly on these embedding vectors. This approach has two shortcomings. First, such methods consider single input sequences in isolation and are unable to put an individual embedding vector in relation to vectors outside the current local context of use. Second, the high performance of these models relies on fine-tuning the embedding model in conjunction with the classifier, which may not always be feasible due to the size or inaccessibility of the underlying feature-generation model. It is thus desirable, given a collection of embedding vectors of a corpus, i.e. a datastore, to find features of each vector that describe its relation to other, similar vectors in the datastore. With this in mind, we introduce complexity measures of the local topology of the latent space of a contextual language model with respect to a given datastore. The effectiveness of our features is demonstrated through their application to dialogue term extraction. Our work continues a line of research that explores the manifold hypothesis for word embeddings, demonstrating that local structure in the space carved out by word embeddings can be exploited to infer semantic properties.</abstract>
<identifier type="citekey">ruppik-etal-2024-local</identifier>
<location>
<url>https://aclanthology.org/2024.sigdial-1.31</url>
</location>
<part>
<date>2024-09</date>
<extent unit="page">
<start>344</start>
<end>356</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Local Topology Measures of Contextual Language Model Latent Spaces with Applications to Dialogue Term Extraction
%A Ruppik, Benjamin Matthias
%A Heck, Michael
%A van Niekerk, Carel
%A Vukovic, Renato
%A Lin, Hsien-chin
%A Feng, Shutong
%A Zibrowius, Marcus
%A Gasic, Milica
%Y Kawahara, Tatsuya
%Y Demberg, Vera
%Y Ultes, Stefan
%Y Inoue, Koji
%Y Mehri, Shikib
%Y Howcroft, David
%Y Komatani, Kazunori
%S Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2024
%8 September
%I Association for Computational Linguistics
%C Kyoto, Japan
%F ruppik-etal-2024-local
%X A common approach for sequence tagging tasks based on contextual word representations is to train a machine learning classifier directly on these embedding vectors. This approach has two shortcomings. First, such methods consider single input sequences in isolation and are unable to put an individual embedding vector in relation to vectors outside the current local context of use. Second, the high performance of these models relies on fine-tuning the embedding model in conjunction with the classifier, which may not always be feasible due to the size or inaccessibility of the underlying feature-generation model. It is thus desirable, given a collection of embedding vectors of a corpus, i.e. a datastore, to find features of each vector that describe its relation to other, similar vectors in the datastore. With this in mind, we introduce complexity measures of the local topology of the latent space of a contextual language model with respect to a given datastore. The effectiveness of our features is demonstrated through their application to dialogue term extraction. Our work continues a line of research that explores the manifold hypothesis for word embeddings, demonstrating that local structure in the space carved out by word embeddings can be exploited to infer semantic properties.
%U https://aclanthology.org/2024.sigdial-1.31
%P 344-356
Markdown (Informal)
[Local Topology Measures of Contextual Language Model Latent Spaces with Applications to Dialogue Term Extraction](https://aclanthology.org/2024.sigdial-1.31) (Ruppik et al., SIGDIAL 2024)
ACL
- Benjamin Matthias Ruppik, Michael Heck, Carel van Niekerk, Renato Vukovic, Hsien-chin Lin, Shutong Feng, Marcus Zibrowius, and Milica Gasic. 2024. Local Topology Measures of Contextual Language Model Latent Spaces with Applications to Dialogue Term Extraction. In Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 344–356, Kyoto, Japan. Association for Computational Linguistics.