@inproceedings{dakota-kubler-2024-bits-pieces,
title = "Bits and Pieces: Investigating the Effects of Subwords in Multi-task Parsing across Languages and Domains",
author = {Dakota, Daniel and
K{\"u}bler, Sandra},
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.215",
pages = "2397--2409",
abstract = "Neural parsing is very dependent on the underlying language model. However, very little is known about how choices in the language model affect parsing performance, especially in multi-task learning. We investigate questions on how the choice of subwords affects parsing, how subword sharing is responsible for gains or negative transfer in a multi-task setting where each task is parsing of a specific domain of the same language. More specifically, we investigate these issues across four languages: English, German, Italian, and Turkish. We find a general preference for averaged or last subwords across languages and domains. However, specific POS tags may require different subwords, and the distributional overlap between subwords across domains is perhaps a more influential factor in determining positive or negative transfer than discrepancies in the data sizes.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dakota-kubler-2024-bits-pieces">
<titleInfo>
<title>Bits and Pieces: Investigating the Effects of Subwords in Multi-task Parsing across Languages and Domains</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Dakota</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandra</namePart>
<namePart type="family">Kübler</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>Neural parsing is very dependent on the underlying language model. However, very little is known about how choices in the language model affect parsing performance, especially in multi-task learning. We investigate questions on how the choice of subwords affects parsing, how subword sharing is responsible for gains or negative transfer in a multi-task setting where each task is parsing of a specific domain of the same language. More specifically, we investigate these issues across four languages: English, German, Italian, and Turkish. We find a general preference for averaged or last subwords across languages and domains. However, specific POS tags may require different subwords, and the distributional overlap between subwords across domains is perhaps a more influential factor in determining positive or negative transfer than discrepancies in the data sizes.</abstract>
<identifier type="citekey">dakota-kubler-2024-bits-pieces</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.215</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>2397</start>
<end>2409</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bits and Pieces: Investigating the Effects of Subwords in Multi-task Parsing across Languages and Domains
%A Dakota, Daniel
%A Kübler, Sandra
%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 dakota-kubler-2024-bits-pieces
%X Neural parsing is very dependent on the underlying language model. However, very little is known about how choices in the language model affect parsing performance, especially in multi-task learning. We investigate questions on how the choice of subwords affects parsing, how subword sharing is responsible for gains or negative transfer in a multi-task setting where each task is parsing of a specific domain of the same language. More specifically, we investigate these issues across four languages: English, German, Italian, and Turkish. We find a general preference for averaged or last subwords across languages and domains. However, specific POS tags may require different subwords, and the distributional overlap between subwords across domains is perhaps a more influential factor in determining positive or negative transfer than discrepancies in the data sizes.
%U https://aclanthology.org/2024.lrec-main.215
%P 2397-2409
Markdown (Informal)
[Bits and Pieces: Investigating the Effects of Subwords in Multi-task Parsing across Languages and Domains](https://aclanthology.org/2024.lrec-main.215) (Dakota & Kübler, LREC-COLING 2024)
ACL