@inproceedings{nagata-etal-2023-variance,
title = "Variance Matters: Detecting Semantic Differences without Corpus/Word Alignment",
author = "Nagata, Ryo and
Takamura, Hiroya and
Otani, Naoki and
Kawasaki, Yoshifumi",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-main.965",
doi = "10.18653/v1/2023.emnlp-main.965",
pages = "15609--15622",
abstract = "In this paper, we propose methods for discovering semantic differences in words appearing in two corpora. The key idea is to measure the coverage of meanings of a word in a corpus through the norm of its mean word vector, which is equivalent to examining a kind of variance of the word vector distribution. The proposed methods do not require alignments between words and/or corpora for comparison that previous methods do. All they require are to compute variance (or norms of mean word vectors) for each word type. Nevertheless, they rival the best-performing system in the SemEval-2020 Task 1. In addition, they are (i) robust for the skew in corpus sizes; (ii) capable of detecting semantic differences in infrequent words; and (iii) effective in pinpointing word instances that have a meaning missing in one of the two corpora under comparison. We show these advantages for historical corpora and also for native/non-native English corpora.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nagata-etal-2023-variance">
<titleInfo>
<title>Variance Matters: Detecting Semantic Differences without Corpus/Word Alignment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ryo</namePart>
<namePart type="family">Nagata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroya</namePart>
<namePart type="family">Takamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoki</namePart>
<namePart type="family">Otani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoshifumi</namePart>
<namePart type="family">Kawasaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we propose methods for discovering semantic differences in words appearing in two corpora. The key idea is to measure the coverage of meanings of a word in a corpus through the norm of its mean word vector, which is equivalent to examining a kind of variance of the word vector distribution. The proposed methods do not require alignments between words and/or corpora for comparison that previous methods do. All they require are to compute variance (or norms of mean word vectors) for each word type. Nevertheless, they rival the best-performing system in the SemEval-2020 Task 1. In addition, they are (i) robust for the skew in corpus sizes; (ii) capable of detecting semantic differences in infrequent words; and (iii) effective in pinpointing word instances that have a meaning missing in one of the two corpora under comparison. We show these advantages for historical corpora and also for native/non-native English corpora.</abstract>
<identifier type="citekey">nagata-etal-2023-variance</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-main.965</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-main.965</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>15609</start>
<end>15622</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Variance Matters: Detecting Semantic Differences without Corpus/Word Alignment
%A Nagata, Ryo
%A Takamura, Hiroya
%A Otani, Naoki
%A Kawasaki, Yoshifumi
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F nagata-etal-2023-variance
%X In this paper, we propose methods for discovering semantic differences in words appearing in two corpora. The key idea is to measure the coverage of meanings of a word in a corpus through the norm of its mean word vector, which is equivalent to examining a kind of variance of the word vector distribution. The proposed methods do not require alignments between words and/or corpora for comparison that previous methods do. All they require are to compute variance (or norms of mean word vectors) for each word type. Nevertheless, they rival the best-performing system in the SemEval-2020 Task 1. In addition, they are (i) robust for the skew in corpus sizes; (ii) capable of detecting semantic differences in infrequent words; and (iii) effective in pinpointing word instances that have a meaning missing in one of the two corpora under comparison. We show these advantages for historical corpora and also for native/non-native English corpora.
%R 10.18653/v1/2023.emnlp-main.965
%U https://aclanthology.org/2023.emnlp-main.965
%U https://doi.org/10.18653/v1/2023.emnlp-main.965
%P 15609-15622
Markdown (Informal)
[Variance Matters: Detecting Semantic Differences without Corpus/Word Alignment](https://aclanthology.org/2023.emnlp-main.965) (Nagata et al., EMNLP 2023)
ACL