@article{apidianaki-2023-word,
title = "From Word Types to Tokens and Back: A Survey of Approaches to Word Meaning Representation and Interpretation",
author = "Apidianaki, Marianna",
journal = "Computational Linguistics",
volume = "49",
number = "2",
month = jun,
year = "2023",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/2023.cl-2.7",
doi = "10.1162/coli_a_00474",
pages = "465--523",
abstract = "Vector-based word representation paradigms situate lexical meaning at different levels of abstraction. Distributional and static embedding models generate a single vector per word type, which is an aggregate across the instances of the word in a corpus. Contextual language models, on the contrary, directly capture the meaning of individual word instances. The goal of this survey is to provide an overview of word meaning representation methods, and of the strategies that have been proposed for improving the quality of the generated vectors. These often involve injecting external knowledge about lexical semantic relationships, or refining the vectors to describe different senses. The survey also covers recent approaches for obtaining word type-level representations from token-level ones, and for combining static and contextualized representations. Special focus is given to probing and interpretation studies aimed at discovering the lexical semantic knowledge that is encoded in contextualized representations. The challenges posed by this exploration have motivated the interest towards static embedding derivation from contextualized embeddings, and for methods aimed at improving the similarity estimates that can be drawn from the space of contextual language models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="apidianaki-2023-word">
<titleInfo>
<title>From Word Types to Tokens and Back: A Survey of Approaches to Word Meaning Representation and Interpretation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre authority="bibutilsgt">journal article</genre>
<relatedItem type="host">
<titleInfo>
<title>Computational Linguistics</title>
</titleInfo>
<originInfo>
<issuance>continuing</issuance>
<publisher>MIT Press</publisher>
<place>
<placeTerm type="text">Cambridge, MA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">periodical</genre>
<genre authority="bibutilsgt">academic journal</genre>
</relatedItem>
<abstract>Vector-based word representation paradigms situate lexical meaning at different levels of abstraction. Distributional and static embedding models generate a single vector per word type, which is an aggregate across the instances of the word in a corpus. Contextual language models, on the contrary, directly capture the meaning of individual word instances. The goal of this survey is to provide an overview of word meaning representation methods, and of the strategies that have been proposed for improving the quality of the generated vectors. These often involve injecting external knowledge about lexical semantic relationships, or refining the vectors to describe different senses. The survey also covers recent approaches for obtaining word type-level representations from token-level ones, and for combining static and contextualized representations. Special focus is given to probing and interpretation studies aimed at discovering the lexical semantic knowledge that is encoded in contextualized representations. The challenges posed by this exploration have motivated the interest towards static embedding derivation from contextualized embeddings, and for methods aimed at improving the similarity estimates that can be drawn from the space of contextual language models.</abstract>
<identifier type="citekey">apidianaki-2023-word</identifier>
<identifier type="doi">10.1162/coli_a_00474</identifier>
<location>
<url>https://aclanthology.org/2023.cl-2.7</url>
</location>
<part>
<date>2023-06</date>
<detail type="volume"><number>49</number></detail>
<detail type="issue"><number>2</number></detail>
<extent unit="page">
<start>465</start>
<end>523</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T From Word Types to Tokens and Back: A Survey of Approaches to Word Meaning Representation and Interpretation
%A Apidianaki, Marianna
%J Computational Linguistics
%D 2023
%8 June
%V 49
%N 2
%I MIT Press
%C Cambridge, MA
%F apidianaki-2023-word
%X Vector-based word representation paradigms situate lexical meaning at different levels of abstraction. Distributional and static embedding models generate a single vector per word type, which is an aggregate across the instances of the word in a corpus. Contextual language models, on the contrary, directly capture the meaning of individual word instances. The goal of this survey is to provide an overview of word meaning representation methods, and of the strategies that have been proposed for improving the quality of the generated vectors. These often involve injecting external knowledge about lexical semantic relationships, or refining the vectors to describe different senses. The survey also covers recent approaches for obtaining word type-level representations from token-level ones, and for combining static and contextualized representations. Special focus is given to probing and interpretation studies aimed at discovering the lexical semantic knowledge that is encoded in contextualized representations. The challenges posed by this exploration have motivated the interest towards static embedding derivation from contextualized embeddings, and for methods aimed at improving the similarity estimates that can be drawn from the space of contextual language models.
%R 10.1162/coli_a_00474
%U https://aclanthology.org/2023.cl-2.7
%U https://doi.org/10.1162/coli_a_00474
%P 465-523
Markdown (Informal)
[From Word Types to Tokens and Back: A Survey of Approaches to Word Meaning Representation and Interpretation](https://aclanthology.org/2023.cl-2.7) (Apidianaki, CL 2023)
ACL