@inproceedings{bassignana-etal-2024-encode-domain,
title = "How to Encode Domain Information in Relation Classification",
author = "Bassignana, Elisa and
Gascou, Viggo Unmack and
Laustsen, Frida N{\o}hr and
Kristensen, Gustav and
Petersen, Marie Haahr and
van der Goot, Rob and
Plank, Barbara",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.728",
pages = "8301--8306",
abstract = "Current language models require a lot of training data to obtain high performance. For Relation Classification (RC), many datasets are domain-specific, so combining datasets to obtain better performance is non-trivial. We explore a multi-domain training setup for RC, and attempt to improve performance by encoding domain information. Our proposed models improve {\textgreater} 2 Macro-F1 against the baseline setup, and our analysis reveals that not all the labels benefit the same: The classes which occupy a similar space across domains (i.e., their interpretation is close across them, for example {``}physical{''}) benefit the least, while domain-dependent relations (e.g., {``}part-of{''}) improve the most when encoding domain information.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bassignana-etal-2024-encode-domain">
<titleInfo>
<title>How to Encode Domain Information in Relation Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elisa</namePart>
<namePart type="family">Bassignana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viggo</namePart>
<namePart type="given">Unmack</namePart>
<namePart type="family">Gascou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frida</namePart>
<namePart type="given">Nøhr</namePart>
<namePart type="family">Laustsen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gustav</namePart>
<namePart type="family">Kristensen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="given">Haahr</namePart>
<namePart type="family">Petersen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rob</namePart>
<namePart type="family">van der Goot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Plank</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</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">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Current language models require a lot of training data to obtain high performance. For Relation Classification (RC), many datasets are domain-specific, so combining datasets to obtain better performance is non-trivial. We explore a multi-domain training setup for RC, and attempt to improve performance by encoding domain information. Our proposed models improve \textgreater 2 Macro-F1 against the baseline setup, and our analysis reveals that not all the labels benefit the same: The classes which occupy a similar space across domains (i.e., their interpretation is close across them, for example “physical”) benefit the least, while domain-dependent relations (e.g., “part-of”) improve the most when encoding domain information.</abstract>
<identifier type="citekey">bassignana-etal-2024-encode-domain</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.728</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>8301</start>
<end>8306</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T How to Encode Domain Information in Relation Classification
%A Bassignana, Elisa
%A Gascou, Viggo Unmack
%A Laustsen, Frida Nøhr
%A Kristensen, Gustav
%A Petersen, Marie Haahr
%A van der Goot, Rob
%A Plank, Barbara
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F bassignana-etal-2024-encode-domain
%X Current language models require a lot of training data to obtain high performance. For Relation Classification (RC), many datasets are domain-specific, so combining datasets to obtain better performance is non-trivial. We explore a multi-domain training setup for RC, and attempt to improve performance by encoding domain information. Our proposed models improve \textgreater 2 Macro-F1 against the baseline setup, and our analysis reveals that not all the labels benefit the same: The classes which occupy a similar space across domains (i.e., their interpretation is close across them, for example “physical”) benefit the least, while domain-dependent relations (e.g., “part-of”) improve the most when encoding domain information.
%U https://aclanthology.org/2024.lrec-main.728
%P 8301-8306
Markdown (Informal)
[How to Encode Domain Information in Relation Classification](https://aclanthology.org/2024.lrec-main.728) (Bassignana et al., LREC-COLING 2024)
ACL
- Elisa Bassignana, Viggo Unmack Gascou, Frida Nøhr Laustsen, Gustav Kristensen, Marie Haahr Petersen, Rob van der Goot, and Barbara Plank. 2024. How to Encode Domain Information in Relation Classification. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 8301–8306, Torino, Italia. ELRA and ICCL.