@inproceedings{schneider-etal-2020-language,
title = "Is Language Modeling Enough? Evaluating Effective Embedding Combinations",
author = "Schneider, Rudolf and
Oberhauser, Tom and
Grundmann, Paul and
Gers, Felix Alexander and
Loeser, Alexander and
Staab, Steffen",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.583",
pages = "4739--4748",
abstract = "Universal embeddings, such as BERT or ELMo, are useful for a broad set of natural language processing tasks like text classification or sentiment analysis. Moreover, specialized embeddings also exist for tasks like topic modeling or named entity disambiguation. We study if we can complement these universal embeddings with specialized embeddings. We conduct an in-depth evaluation of nine well known natural language understanding tasks with SentEval. Also, we extend SentEval with two additional tasks to the medical domain. We present PubMedSection, a novel topic classification dataset focussed on the biomedical domain. Our comprehensive analysis covers 11 tasks and combinations of six embeddings. We report that combined embeddings outperform state of the art universal embeddings without any embedding fine-tuning. We observe that adding topic model based embeddings helps for most tasks and that differing pre-training tasks encode complementary features. Moreover, we present new state of the art results on the MPQA and SUBJ tasks in SentEval.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="schneider-etal-2020-language">
<titleInfo>
<title>Is Language Modeling Enough? Evaluating Effective Embedding Combinations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rudolf</namePart>
<namePart type="family">Schneider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Oberhauser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Grundmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felix</namePart>
<namePart type="given">Alexander</namePart>
<namePart type="family">Gers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Loeser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steffen</namePart>
<namePart type="family">Staab</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Universal embeddings, such as BERT or ELMo, are useful for a broad set of natural language processing tasks like text classification or sentiment analysis. Moreover, specialized embeddings also exist for tasks like topic modeling or named entity disambiguation. We study if we can complement these universal embeddings with specialized embeddings. We conduct an in-depth evaluation of nine well known natural language understanding tasks with SentEval. Also, we extend SentEval with two additional tasks to the medical domain. We present PubMedSection, a novel topic classification dataset focussed on the biomedical domain. Our comprehensive analysis covers 11 tasks and combinations of six embeddings. We report that combined embeddings outperform state of the art universal embeddings without any embedding fine-tuning. We observe that adding topic model based embeddings helps for most tasks and that differing pre-training tasks encode complementary features. Moreover, we present new state of the art results on the MPQA and SUBJ tasks in SentEval.</abstract>
<identifier type="citekey">schneider-etal-2020-language</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.583</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>4739</start>
<end>4748</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Is Language Modeling Enough? Evaluating Effective Embedding Combinations
%A Schneider, Rudolf
%A Oberhauser, Tom
%A Grundmann, Paul
%A Gers, Felix Alexander
%A Loeser, Alexander
%A Staab, Steffen
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F schneider-etal-2020-language
%X Universal embeddings, such as BERT or ELMo, are useful for a broad set of natural language processing tasks like text classification or sentiment analysis. Moreover, specialized embeddings also exist for tasks like topic modeling or named entity disambiguation. We study if we can complement these universal embeddings with specialized embeddings. We conduct an in-depth evaluation of nine well known natural language understanding tasks with SentEval. Also, we extend SentEval with two additional tasks to the medical domain. We present PubMedSection, a novel topic classification dataset focussed on the biomedical domain. Our comprehensive analysis covers 11 tasks and combinations of six embeddings. We report that combined embeddings outperform state of the art universal embeddings without any embedding fine-tuning. We observe that adding topic model based embeddings helps for most tasks and that differing pre-training tasks encode complementary features. Moreover, we present new state of the art results on the MPQA and SUBJ tasks in SentEval.
%U https://aclanthology.org/2020.lrec-1.583
%P 4739-4748
Markdown (Informal)
[Is Language Modeling Enough? Evaluating Effective Embedding Combinations](https://aclanthology.org/2020.lrec-1.583) (Schneider et al., LREC 2020)
ACL