@inproceedings{apallius-de-vos-etal-2021-comparing,
title = "Comparing in context: Improving cosine similarity measures with a metric tensor",
author = "Apallius de Vos, Isa M. and
van den Boogerd, Ghislaine L. and
Fennema, Mara D. and
Correia, Adriana",
editor = "Bandyopadhyay, Sivaji and
Devi, Sobha Lalitha and
Bhattacharyya, Pushpak",
booktitle = "Proceedings of the 18th International Conference on Natural Language Processing (ICON)",
month = dec,
year = "2021",
address = "National Institute of Technology Silchar, Silchar, India",
publisher = "NLP Association of India (NLPAI)",
url = "https://aclanthology.org/2021.icon-main.17",
pages = "128--138",
abstract = "Cosine similarity is a widely used measure of the relatedness of pre-trained word embeddings, trained on a language modeling goal. Datasets such as WordSim-353 and SimLex-999 rate how similar words are according to human annotators, and as such are often used to evaluate the performance of language models. Thus, any improvement on the word similarity task requires an improved word representation. In this paper, we propose instead the use of an extended cosine similarity measure to improve performance on that task, with gains in interpretability. We explore the hypothesis that this approach is particularly useful if the word-similarity pairs share the same context, for which distinct contextualized similarity measures can be learned. We first use the dataset of Richie et al. (2020) to learn contextualized metrics and compare the results with the baseline values obtained using the standard cosine similarity measure, which consistently shows improvement. We also train a contextualized similarity measure for both SimLex-999 and WordSim-353, comparing the results with the corresponding baselines, and using these datasets as independent test sets for the all-context similarity measure learned on the contextualized dataset, obtaining positive results for a number of tests.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="apallius-de-vos-etal-2021-comparing">
<titleInfo>
<title>Comparing in context: Improving cosine similarity measures with a metric tensor</title>
</titleInfo>
<name type="personal">
<namePart type="given">Isa</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Apallius de Vos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ghislaine</namePart>
<namePart type="given">L</namePart>
<namePart type="family">van den Boogerd</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mara</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Fennema</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adriana</namePart>
<namePart type="family">Correia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th International Conference on Natural Language Processing (ICON)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sivaji</namePart>
<namePart type="family">Bandyopadhyay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sobha</namePart>
<namePart type="given">Lalitha</namePart>
<namePart type="family">Devi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>NLP Association of India (NLPAI)</publisher>
<place>
<placeTerm type="text">National Institute of Technology Silchar, Silchar, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Cosine similarity is a widely used measure of the relatedness of pre-trained word embeddings, trained on a language modeling goal. Datasets such as WordSim-353 and SimLex-999 rate how similar words are according to human annotators, and as such are often used to evaluate the performance of language models. Thus, any improvement on the word similarity task requires an improved word representation. In this paper, we propose instead the use of an extended cosine similarity measure to improve performance on that task, with gains in interpretability. We explore the hypothesis that this approach is particularly useful if the word-similarity pairs share the same context, for which distinct contextualized similarity measures can be learned. We first use the dataset of Richie et al. (2020) to learn contextualized metrics and compare the results with the baseline values obtained using the standard cosine similarity measure, which consistently shows improvement. We also train a contextualized similarity measure for both SimLex-999 and WordSim-353, comparing the results with the corresponding baselines, and using these datasets as independent test sets for the all-context similarity measure learned on the contextualized dataset, obtaining positive results for a number of tests.</abstract>
<identifier type="citekey">apallius-de-vos-etal-2021-comparing</identifier>
<location>
<url>https://aclanthology.org/2021.icon-main.17</url>
</location>
<part>
<date>2021-12</date>
<extent unit="page">
<start>128</start>
<end>138</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Comparing in context: Improving cosine similarity measures with a metric tensor
%A Apallius de Vos, Isa M.
%A van den Boogerd, Ghislaine L.
%A Fennema, Mara D.
%A Correia, Adriana
%Y Bandyopadhyay, Sivaji
%Y Devi, Sobha Lalitha
%Y Bhattacharyya, Pushpak
%S Proceedings of the 18th International Conference on Natural Language Processing (ICON)
%D 2021
%8 December
%I NLP Association of India (NLPAI)
%C National Institute of Technology Silchar, Silchar, India
%F apallius-de-vos-etal-2021-comparing
%X Cosine similarity is a widely used measure of the relatedness of pre-trained word embeddings, trained on a language modeling goal. Datasets such as WordSim-353 and SimLex-999 rate how similar words are according to human annotators, and as such are often used to evaluate the performance of language models. Thus, any improvement on the word similarity task requires an improved word representation. In this paper, we propose instead the use of an extended cosine similarity measure to improve performance on that task, with gains in interpretability. We explore the hypothesis that this approach is particularly useful if the word-similarity pairs share the same context, for which distinct contextualized similarity measures can be learned. We first use the dataset of Richie et al. (2020) to learn contextualized metrics and compare the results with the baseline values obtained using the standard cosine similarity measure, which consistently shows improvement. We also train a contextualized similarity measure for both SimLex-999 and WordSim-353, comparing the results with the corresponding baselines, and using these datasets as independent test sets for the all-context similarity measure learned on the contextualized dataset, obtaining positive results for a number of tests.
%U https://aclanthology.org/2021.icon-main.17
%P 128-138
Markdown (Informal)
[Comparing in context: Improving cosine similarity measures with a metric tensor](https://aclanthology.org/2021.icon-main.17) (Apallius de Vos et al., ICON 2021)
ACL