@inproceedings{wang-etal-2021-deriving,
title = "Deriving Word Vectors from Contextualized Language Models using Topic-Aware Mention Selection",
author = "Wang, Yixiao and
Bouraoui, Zied and
Espinosa Anke, Luis and
Schockaert, Steven",
editor = "Rogers, Anna and
Calixto, Iacer and
Vuli{\'c}, Ivan and
Saphra, Naomi and
Kassner, Nora and
Camburu, Oana-Maria and
Bansal, Trapit and
Shwartz, Vered",
booktitle = "Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.repl4nlp-1.19",
doi = "10.18653/v1/2021.repl4nlp-1.19",
pages = "185--194",
abstract = "One of the long-standing challenges in lexical semantics consists in learning representations of words which reflect their semantic properties. The remarkable success of word embeddings for this purpose suggests that high-quality representations can be obtained by summarizing the sentence contexts of word mentions. In this paper, we propose a method for learning word representations that follows this basic strategy, but differs from standard word embeddings in two important ways. First, we take advantage of contextualized language models (CLMs) rather than bags of word vectors to encode contexts. Second, rather than learning a word vector directly, we use a topic model to partition the contexts in which words appear, and then learn different topic-specific vectors for each word. Finally, we use a task-specific supervision signal to make a soft selection of the resulting vectors. We show that this simple strategy leads to high-quality word vectors, which are more predictive of semantic properties than word embeddings and existing CLM-based strategies.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2021-deriving">
<titleInfo>
<title>Deriving Word Vectors from Contextualized Language Models using Topic-Aware Mention Selection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yixiao</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zied</namePart>
<namePart type="family">Bouraoui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Espinosa Anke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iacer</namePart>
<namePart type="family">Calixto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Vulić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naomi</namePart>
<namePart type="family">Saphra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nora</namePart>
<namePart type="family">Kassner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oana-Maria</namePart>
<namePart type="family">Camburu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trapit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vered</namePart>
<namePart type="family">Shwartz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>One of the long-standing challenges in lexical semantics consists in learning representations of words which reflect their semantic properties. The remarkable success of word embeddings for this purpose suggests that high-quality representations can be obtained by summarizing the sentence contexts of word mentions. In this paper, we propose a method for learning word representations that follows this basic strategy, but differs from standard word embeddings in two important ways. First, we take advantage of contextualized language models (CLMs) rather than bags of word vectors to encode contexts. Second, rather than learning a word vector directly, we use a topic model to partition the contexts in which words appear, and then learn different topic-specific vectors for each word. Finally, we use a task-specific supervision signal to make a soft selection of the resulting vectors. We show that this simple strategy leads to high-quality word vectors, which are more predictive of semantic properties than word embeddings and existing CLM-based strategies.</abstract>
<identifier type="citekey">wang-etal-2021-deriving</identifier>
<identifier type="doi">10.18653/v1/2021.repl4nlp-1.19</identifier>
<location>
<url>https://aclanthology.org/2021.repl4nlp-1.19</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>185</start>
<end>194</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Deriving Word Vectors from Contextualized Language Models using Topic-Aware Mention Selection
%A Wang, Yixiao
%A Bouraoui, Zied
%A Espinosa Anke, Luis
%A Schockaert, Steven
%Y Rogers, Anna
%Y Calixto, Iacer
%Y Vulić, Ivan
%Y Saphra, Naomi
%Y Kassner, Nora
%Y Camburu, Oana-Maria
%Y Bansal, Trapit
%Y Shwartz, Vered
%S Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F wang-etal-2021-deriving
%X One of the long-standing challenges in lexical semantics consists in learning representations of words which reflect their semantic properties. The remarkable success of word embeddings for this purpose suggests that high-quality representations can be obtained by summarizing the sentence contexts of word mentions. In this paper, we propose a method for learning word representations that follows this basic strategy, but differs from standard word embeddings in two important ways. First, we take advantage of contextualized language models (CLMs) rather than bags of word vectors to encode contexts. Second, rather than learning a word vector directly, we use a topic model to partition the contexts in which words appear, and then learn different topic-specific vectors for each word. Finally, we use a task-specific supervision signal to make a soft selection of the resulting vectors. We show that this simple strategy leads to high-quality word vectors, which are more predictive of semantic properties than word embeddings and existing CLM-based strategies.
%R 10.18653/v1/2021.repl4nlp-1.19
%U https://aclanthology.org/2021.repl4nlp-1.19
%U https://doi.org/10.18653/v1/2021.repl4nlp-1.19
%P 185-194
Markdown (Informal)
[Deriving Word Vectors from Contextualized Language Models using Topic-Aware Mention Selection](https://aclanthology.org/2021.repl4nlp-1.19) (Wang et al., RepL4NLP 2021)
ACL