@inproceedings{fakharian-cook-2021-contextualized,
title = "Contextualized Embeddings Encode Monolingual and Cross-lingual Knowledge of Idiomaticity",
author = "Fakharian, Samin and
Cook, Paul",
editor = "Cook, Paul and
Mitrovi{\'c}, Jelena and
Escart{\'\i}n, Carla Parra and
Vaidya, Ashwini and
Osenova, Petya and
Taslimipoor, Shiva and
Ramisch, Carlos",
booktitle = "Proceedings of the 17th Workshop on Multiword Expressions (MWE 2021)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.mwe-1.4",
doi = "10.18653/v1/2021.mwe-1.4",
pages = "23--32",
abstract = "Potentially idiomatic expressions (PIEs) are ambiguous between non-compositional idiomatic interpretations and transparent literal interpretations. For example, {``}hit the road{''} can have an idiomatic meaning corresponding to {`}start a journey{'} or have a literal interpretation. In this paper we propose a supervised model based on contextualized embeddings for predicting whether usages of PIEs are idiomatic or literal. We consider monolingual experiments for English and Russian, and show that the proposed model outperforms previous approaches, including in the case that the model is tested on instances of PIE types that were not observed during training. We then consider cross-lingual experiments in which the model is trained on PIE instances in one language, English or Russian, and tested on the other language. We find that the model outperforms baselines in this setting. These findings suggest that contextualized embeddings are able to learn representations that encode knowledge of idiomaticity that is not restricted to specific expressions, nor to a specific language.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fakharian-cook-2021-contextualized">
<titleInfo>
<title>Contextualized Embeddings Encode Monolingual and Cross-lingual Knowledge of Idiomaticity</title>
</titleInfo>
<name type="personal">
<namePart type="given">Samin</namePart>
<namePart type="family">Fakharian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Cook</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 17th Workshop on Multiword Expressions (MWE 2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Cook</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jelena</namePart>
<namePart type="family">Mitrović</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carla</namePart>
<namePart type="given">Parra</namePart>
<namePart type="family">Escartín</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashwini</namePart>
<namePart type="family">Vaidya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Petya</namePart>
<namePart type="family">Osenova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shiva</namePart>
<namePart type="family">Taslimipoor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carlos</namePart>
<namePart type="family">Ramisch</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>Potentially idiomatic expressions (PIEs) are ambiguous between non-compositional idiomatic interpretations and transparent literal interpretations. For example, “hit the road” can have an idiomatic meaning corresponding to ‘start a journey’ or have a literal interpretation. In this paper we propose a supervised model based on contextualized embeddings for predicting whether usages of PIEs are idiomatic or literal. We consider monolingual experiments for English and Russian, and show that the proposed model outperforms previous approaches, including in the case that the model is tested on instances of PIE types that were not observed during training. We then consider cross-lingual experiments in which the model is trained on PIE instances in one language, English or Russian, and tested on the other language. We find that the model outperforms baselines in this setting. These findings suggest that contextualized embeddings are able to learn representations that encode knowledge of idiomaticity that is not restricted to specific expressions, nor to a specific language.</abstract>
<identifier type="citekey">fakharian-cook-2021-contextualized</identifier>
<identifier type="doi">10.18653/v1/2021.mwe-1.4</identifier>
<location>
<url>https://aclanthology.org/2021.mwe-1.4</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>23</start>
<end>32</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Contextualized Embeddings Encode Monolingual and Cross-lingual Knowledge of Idiomaticity
%A Fakharian, Samin
%A Cook, Paul
%Y Cook, Paul
%Y Mitrović, Jelena
%Y Escartín, Carla Parra
%Y Vaidya, Ashwini
%Y Osenova, Petya
%Y Taslimipoor, Shiva
%Y Ramisch, Carlos
%S Proceedings of the 17th Workshop on Multiword Expressions (MWE 2021)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F fakharian-cook-2021-contextualized
%X Potentially idiomatic expressions (PIEs) are ambiguous between non-compositional idiomatic interpretations and transparent literal interpretations. For example, “hit the road” can have an idiomatic meaning corresponding to ‘start a journey’ or have a literal interpretation. In this paper we propose a supervised model based on contextualized embeddings for predicting whether usages of PIEs are idiomatic or literal. We consider monolingual experiments for English and Russian, and show that the proposed model outperforms previous approaches, including in the case that the model is tested on instances of PIE types that were not observed during training. We then consider cross-lingual experiments in which the model is trained on PIE instances in one language, English or Russian, and tested on the other language. We find that the model outperforms baselines in this setting. These findings suggest that contextualized embeddings are able to learn representations that encode knowledge of idiomaticity that is not restricted to specific expressions, nor to a specific language.
%R 10.18653/v1/2021.mwe-1.4
%U https://aclanthology.org/2021.mwe-1.4
%U https://doi.org/10.18653/v1/2021.mwe-1.4
%P 23-32
Markdown (Informal)
[Contextualized Embeddings Encode Monolingual and Cross-lingual Knowledge of Idiomaticity](https://aclanthology.org/2021.mwe-1.4) (Fakharian & Cook, MWE 2021)
ACL