@inproceedings{aljanaideh-etal-2020-contextualized,
title = "Contextualized Embeddings for Enriching Linguistic Analyses on Politeness",
author = "Aljanaideh, Ahmad and
Fosler-Lussier, Eric and
de Marneffe, Marie-Catherine",
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.198",
doi = "10.18653/v1/2020.coling-main.198",
pages = "2181--2190",
abstract = "Linguistic analyses in natural language processing (NLP) have often been performed around the static notion of words where the context (surrounding words) is not considered. For example, previous analyses on politeness have focused on comparing the use of static words such as personal pronouns across (im)polite requests without taking the context of those words into account. Current word embeddings in NLP do capture context and thus can be leveraged to enrich linguistic analyses. In this work, we introduce a model which leverages the pre-trained BERT model to cluster contextualized representations of a word based on (1) the context in which the word appears and (2) the labels of items the word occurs in. Using politeness as case study, this model is able to automatically discover interpretable, fine-grained context patterns of words, some of which align with existing theories on politeness. Our model further discovers novel finer-grained patterns associated with (im)polite language. For example, the word please can occur in impolite contexts that are predictable from BERT clustering. The approach proposed here is validated by showing that features based on fine-grained patterns inferred from the clustering improve over politeness-word baselines.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aljanaideh-etal-2020-contextualized">
<titleInfo>
<title>Contextualized Embeddings for Enriching Linguistic Analyses on Politeness</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ahmad</namePart>
<namePart type="family">Aljanaideh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Fosler-Lussier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</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>Linguistic analyses in natural language processing (NLP) have often been performed around the static notion of words where the context (surrounding words) is not considered. For example, previous analyses on politeness have focused on comparing the use of static words such as personal pronouns across (im)polite requests without taking the context of those words into account. Current word embeddings in NLP do capture context and thus can be leveraged to enrich linguistic analyses. In this work, we introduce a model which leverages the pre-trained BERT model to cluster contextualized representations of a word based on (1) the context in which the word appears and (2) the labels of items the word occurs in. Using politeness as case study, this model is able to automatically discover interpretable, fine-grained context patterns of words, some of which align with existing theories on politeness. Our model further discovers novel finer-grained patterns associated with (im)polite language. For example, the word please can occur in impolite contexts that are predictable from BERT clustering. The approach proposed here is validated by showing that features based on fine-grained patterns inferred from the clustering improve over politeness-word baselines.</abstract>
<identifier type="citekey">aljanaideh-etal-2020-contextualized</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.198</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.198</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>2181</start>
<end>2190</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Contextualized Embeddings for Enriching Linguistic Analyses on Politeness
%A Aljanaideh, Ahmad
%A Fosler-Lussier, Eric
%A de Marneffe, Marie-Catherine
%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 aljanaideh-etal-2020-contextualized
%X Linguistic analyses in natural language processing (NLP) have often been performed around the static notion of words where the context (surrounding words) is not considered. For example, previous analyses on politeness have focused on comparing the use of static words such as personal pronouns across (im)polite requests without taking the context of those words into account. Current word embeddings in NLP do capture context and thus can be leveraged to enrich linguistic analyses. In this work, we introduce a model which leverages the pre-trained BERT model to cluster contextualized representations of a word based on (1) the context in which the word appears and (2) the labels of items the word occurs in. Using politeness as case study, this model is able to automatically discover interpretable, fine-grained context patterns of words, some of which align with existing theories on politeness. Our model further discovers novel finer-grained patterns associated with (im)polite language. For example, the word please can occur in impolite contexts that are predictable from BERT clustering. The approach proposed here is validated by showing that features based on fine-grained patterns inferred from the clustering improve over politeness-word baselines.
%R 10.18653/v1/2020.coling-main.198
%U https://aclanthology.org/2020.coling-main.198
%U https://doi.org/10.18653/v1/2020.coling-main.198
%P 2181-2190
Markdown (Informal)
[Contextualized Embeddings for Enriching Linguistic Analyses on Politeness](https://aclanthology.org/2020.coling-main.198) (Aljanaideh et al., COLING 2020)
ACL