@inproceedings{oyama-etal-2024-understanding,
title = "Understanding Higher-Order Correlations Among Semantic Components in Embeddings",
author = "Oyama, Momose and
Yamagiwa, Hiroaki and
Shimodaira, Hidetoshi",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-main.169",
pages = "2883--2899",
abstract = "Independent Component Analysis (ICA) offers interpretable semantic components of embeddings.While ICA theory assumes that embeddings can be linearly decomposed into independent components, real-world data often do not satisfy this assumption. Consequently, non-independencies remain between the estimated components, which ICA cannot eliminate. We quantified these non-independencies using higher-order correlations and demonstrated that when the higher-order correlation between two components is large, it indicates a strong semantic association between them, along with many words sharing common meanings with both components. The entire structure of non-independencies was visualized using a maximum spanning tree of semantic components. These findings provide deeper insights into embeddings through ICA.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="oyama-etal-2024-understanding">
<titleInfo>
<title>Understanding Higher-Order Correlations Among Semantic Components in Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Momose</namePart>
<namePart type="family">Oyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroaki</namePart>
<namePart type="family">Yamagiwa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hidetoshi</namePart>
<namePart type="family">Shimodaira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Independent Component Analysis (ICA) offers interpretable semantic components of embeddings.While ICA theory assumes that embeddings can be linearly decomposed into independent components, real-world data often do not satisfy this assumption. Consequently, non-independencies remain between the estimated components, which ICA cannot eliminate. We quantified these non-independencies using higher-order correlations and demonstrated that when the higher-order correlation between two components is large, it indicates a strong semantic association between them, along with many words sharing common meanings with both components. The entire structure of non-independencies was visualized using a maximum spanning tree of semantic components. These findings provide deeper insights into embeddings through ICA.</abstract>
<identifier type="citekey">oyama-etal-2024-understanding</identifier>
<location>
<url>https://aclanthology.org/2024.emnlp-main.169</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>2883</start>
<end>2899</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Understanding Higher-Order Correlations Among Semantic Components in Embeddings
%A Oyama, Momose
%A Yamagiwa, Hiroaki
%A Shimodaira, Hidetoshi
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F oyama-etal-2024-understanding
%X Independent Component Analysis (ICA) offers interpretable semantic components of embeddings.While ICA theory assumes that embeddings can be linearly decomposed into independent components, real-world data often do not satisfy this assumption. Consequently, non-independencies remain between the estimated components, which ICA cannot eliminate. We quantified these non-independencies using higher-order correlations and demonstrated that when the higher-order correlation between two components is large, it indicates a strong semantic association between them, along with many words sharing common meanings with both components. The entire structure of non-independencies was visualized using a maximum spanning tree of semantic components. These findings provide deeper insights into embeddings through ICA.
%U https://aclanthology.org/2024.emnlp-main.169
%P 2883-2899
Markdown (Informal)
[Understanding Higher-Order Correlations Among Semantic Components in Embeddings](https://aclanthology.org/2024.emnlp-main.169) (Oyama et al., EMNLP 2024)
ACL