@inproceedings{jadhav-etal-2020-lexical,
title = "Lexical Relation Mining in Neural Word Embeddings",
author = "Jadhav, Aishwarya and
Amir, Yifat and
Pardos, Zachary",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.112",
doi = "10.18653/v1/2020.coling-main.112",
pages = "1299--1311",
abstract = "Work with neural word embeddings and lexical relations has largely focused on confirmatory experiments which use human-curated examples of semantic and syntactic relations to validate against. In this paper, we explore the degree to which lexical relations, such as those found in popular validation sets, can be derived and extended from a variety of neural embeddings using classical clustering methods. We show that the Word2Vec space of word-pairs (i.e., offset vectors) significantly outperforms other more contemporary methods, even in the presence of a large number of noisy offsets. Moreover, we show that via a simple nearest neighbor approach in the offset space, new examples of known relations can be discovered. Our results speak to the amenability of offset vectors from non-contextual neural embeddings to find semantically coherent clusters. This simple approach has implications for the exploration of emergent regularities and their examples, such as emerging trends on social media and their related posts.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jadhav-etal-2020-lexical">
<titleInfo>
<title>Lexical Relation Mining in Neural Word Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aishwarya</namePart>
<namePart type="family">Jadhav</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yifat</namePart>
<namePart type="family">Amir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zachary</namePart>
<namePart type="family">Pardos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Work with neural word embeddings and lexical relations has largely focused on confirmatory experiments which use human-curated examples of semantic and syntactic relations to validate against. In this paper, we explore the degree to which lexical relations, such as those found in popular validation sets, can be derived and extended from a variety of neural embeddings using classical clustering methods. We show that the Word2Vec space of word-pairs (i.e., offset vectors) significantly outperforms other more contemporary methods, even in the presence of a large number of noisy offsets. Moreover, we show that via a simple nearest neighbor approach in the offset space, new examples of known relations can be discovered. Our results speak to the amenability of offset vectors from non-contextual neural embeddings to find semantically coherent clusters. This simple approach has implications for the exploration of emergent regularities and their examples, such as emerging trends on social media and their related posts.</abstract>
<identifier type="citekey">jadhav-etal-2020-lexical</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.112</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.112</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>1299</start>
<end>1311</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Lexical Relation Mining in Neural Word Embeddings
%A Jadhav, Aishwarya
%A Amir, Yifat
%A Pardos, Zachary
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F jadhav-etal-2020-lexical
%X Work with neural word embeddings and lexical relations has largely focused on confirmatory experiments which use human-curated examples of semantic and syntactic relations to validate against. In this paper, we explore the degree to which lexical relations, such as those found in popular validation sets, can be derived and extended from a variety of neural embeddings using classical clustering methods. We show that the Word2Vec space of word-pairs (i.e., offset vectors) significantly outperforms other more contemporary methods, even in the presence of a large number of noisy offsets. Moreover, we show that via a simple nearest neighbor approach in the offset space, new examples of known relations can be discovered. Our results speak to the amenability of offset vectors from non-contextual neural embeddings to find semantically coherent clusters. This simple approach has implications for the exploration of emergent regularities and their examples, such as emerging trends on social media and their related posts.
%R 10.18653/v1/2020.coling-main.112
%U https://aclanthology.org/2020.coling-main.112
%U https://doi.org/10.18653/v1/2020.coling-main.112
%P 1299-1311
Markdown (Informal)
[Lexical Relation Mining in Neural Word Embeddings](https://aclanthology.org/2020.coling-main.112) (Jadhav et al., COLING 2020)
ACL
- Aishwarya Jadhav, Yifat Amir, and Zachary Pardos. 2020. Lexical Relation Mining in Neural Word Embeddings. In Proceedings of the 28th International Conference on Computational Linguistics, pages 1299–1311, Barcelona, Spain (Online). International Committee on Computational Linguistics.