@inproceedings{do-dinh-etal-2018-one,
title = "One Size Fits All? A simple {LSTM} for non-literal token and construction-level classification",
author = "Do Dinh, Erik-L{\^a}n and
Eger, Steffen and
Gurevych, Iryna",
editor = "Alex, Beatrice and
Degaetano-Ortlieb, Stefania and
Feldman, Anna and
Kazantseva, Anna and
Reiter, Nils and
Szpakowicz, Stan",
booktitle = "Proceedings of the Second Joint {SIGHUM} Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature",
month = aug,
year = "2018",
address = "Santa Fe, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-4508/",
pages = "70--80",
abstract = "In this paper, we tackle four different tasks of non-literal language classification: token and construction level metaphor detection, classification of idiomatic use of infinitive-verb compounds, and classification of non-literal particle verbs. One of the tasks operates on the token level, while the three other tasks classify constructions such as {\textquotedblleft}hot topic{\textquotedblright} or {\textquotedblleft}stehen lassen{\textquotedblright} ({\textquotedblleft}to allow sth. to stand{\textquotedblright} vs. {\textquotedblleft}to abandon so.{\textquotedblright}). The two metaphor detection tasks are in English, while the two non-literal language detection tasks are in German. We propose a simple context-encoding LSTM model and show that it outperforms the state-of-the-art on two tasks. Additionally, we experiment with different embeddings for the token level metaphor detection task and find that 1) their performance varies according to the genre, and 2) word2vec embeddings perform best on 3 out of 4 genres, despite being one of the simplest tested model. In summary, we present a large-scale analysis of a neural model for non-literal language classification (i) at different granularities, (ii) in different languages, (iii) over different non-literal language phenomena."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="do-dinh-etal-2018-one">
<titleInfo>
<title>One Size Fits All? A simple LSTM for non-literal token and construction-level classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Erik-Lân</namePart>
<namePart type="family">Do Dinh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steffen</namePart>
<namePart type="family">Eger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iryna</namePart>
<namePart type="family">Gurevych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature</title>
</titleInfo>
<name type="personal">
<namePart type="given">Beatrice</namePart>
<namePart type="family">Alex</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefania</namePart>
<namePart type="family">Degaetano-Ortlieb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Feldman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Kazantseva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nils</namePart>
<namePart type="family">Reiter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stan</namePart>
<namePart type="family">Szpakowicz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Santa Fe, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we tackle four different tasks of non-literal language classification: token and construction level metaphor detection, classification of idiomatic use of infinitive-verb compounds, and classification of non-literal particle verbs. One of the tasks operates on the token level, while the three other tasks classify constructions such as “hot topic” or “stehen lassen” (“to allow sth. to stand” vs. “to abandon so.”). The two metaphor detection tasks are in English, while the two non-literal language detection tasks are in German. We propose a simple context-encoding LSTM model and show that it outperforms the state-of-the-art on two tasks. Additionally, we experiment with different embeddings for the token level metaphor detection task and find that 1) their performance varies according to the genre, and 2) word2vec embeddings perform best on 3 out of 4 genres, despite being one of the simplest tested model. In summary, we present a large-scale analysis of a neural model for non-literal language classification (i) at different granularities, (ii) in different languages, (iii) over different non-literal language phenomena.</abstract>
<identifier type="citekey">do-dinh-etal-2018-one</identifier>
<location>
<url>https://aclanthology.org/W18-4508/</url>
</location>
<part>
<date>2018-08</date>
<extent unit="page">
<start>70</start>
<end>80</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T One Size Fits All? A simple LSTM for non-literal token and construction-level classification
%A Do Dinh, Erik-Lân
%A Eger, Steffen
%A Gurevych, Iryna
%Y Alex, Beatrice
%Y Degaetano-Ortlieb, Stefania
%Y Feldman, Anna
%Y Kazantseva, Anna
%Y Reiter, Nils
%Y Szpakowicz, Stan
%S Proceedings of the Second Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature
%D 2018
%8 August
%I Association for Computational Linguistics
%C Santa Fe, New Mexico
%F do-dinh-etal-2018-one
%X In this paper, we tackle four different tasks of non-literal language classification: token and construction level metaphor detection, classification of idiomatic use of infinitive-verb compounds, and classification of non-literal particle verbs. One of the tasks operates on the token level, while the three other tasks classify constructions such as “hot topic” or “stehen lassen” (“to allow sth. to stand” vs. “to abandon so.”). The two metaphor detection tasks are in English, while the two non-literal language detection tasks are in German. We propose a simple context-encoding LSTM model and show that it outperforms the state-of-the-art on two tasks. Additionally, we experiment with different embeddings for the token level metaphor detection task and find that 1) their performance varies according to the genre, and 2) word2vec embeddings perform best on 3 out of 4 genres, despite being one of the simplest tested model. In summary, we present a large-scale analysis of a neural model for non-literal language classification (i) at different granularities, (ii) in different languages, (iii) over different non-literal language phenomena.
%U https://aclanthology.org/W18-4508/
%P 70-80
Markdown (Informal)
[One Size Fits All? A simple LSTM for non-literal token and construction-level classification](https://aclanthology.org/W18-4508/) (Do Dinh et al., LaTeCH 2018)
ACL