@inproceedings{striebel-etal-2024-domain,
title = "Domain-Weighted Batch Sampling for Neural Dependency Parsing",
author = {Striebel, Jacob and
Dakota, Daniel and
K{\"u}bler, Sandra},
editor = {Bhatia, Archna and
Bouma, Gosse and
Do{\u{g}}ru{\"o}z, A. Seza and
Evang, Kilian and
Garcia, Marcos and
Giouli, Voula and
Han, Lifeng and
Nivre, Joakim and
Rademaker, Alexandre},
booktitle = "Proceedings of the Joint Workshop on Multiword Expressions and Universal Dependencies (MWE-UD) @ LREC-COLING 2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.mwe-1.24",
pages = "198--206",
abstract = "In neural dependency parsing, as well as in the broader field of NLP, domain adaptation remains a challenging problem. When adapting a parser to a target domain, there is a fundamental tension between the need to make use of out-of-domain data and the need to ensure that syntactic characteristic of the target domain are learned. In this work we explore a way to balance these two competing concerns, namely using domain-weighted batch sampling, which allows us to use all available training data, while controlling the probability of sampling in- and out-of-domain data when constructing training batches. We conduct experiments using ten natural language domains and find that domain-weighted batch sampling yields substantial performance improvements in all ten domains compared to a baseline of conventional randomized batch sampling.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="striebel-etal-2024-domain">
<titleInfo>
<title>Domain-Weighted Batch Sampling for Neural Dependency Parsing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jacob</namePart>
<namePart type="family">Striebel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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 Joint Workshop on Multiword Expressions and Universal Dependencies (MWE-UD) @ LREC-COLING 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Archna</namePart>
<namePart type="family">Bhatia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gosse</namePart>
<namePart type="family">Bouma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="given">Seza</namePart>
<namePart type="family">Doğruöz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kilian</namePart>
<namePart type="family">Evang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Garcia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Voula</namePart>
<namePart type="family">Giouli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lifeng</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joakim</namePart>
<namePart type="family">Nivre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandre</namePart>
<namePart type="family">Rademaker</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>In neural dependency parsing, as well as in the broader field of NLP, domain adaptation remains a challenging problem. When adapting a parser to a target domain, there is a fundamental tension between the need to make use of out-of-domain data and the need to ensure that syntactic characteristic of the target domain are learned. In this work we explore a way to balance these two competing concerns, namely using domain-weighted batch sampling, which allows us to use all available training data, while controlling the probability of sampling in- and out-of-domain data when constructing training batches. We conduct experiments using ten natural language domains and find that domain-weighted batch sampling yields substantial performance improvements in all ten domains compared to a baseline of conventional randomized batch sampling.</abstract>
<identifier type="citekey">striebel-etal-2024-domain</identifier>
<location>
<url>https://aclanthology.org/2024.mwe-1.24</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>198</start>
<end>206</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Domain-Weighted Batch Sampling for Neural Dependency Parsing
%A Striebel, Jacob
%A Dakota, Daniel
%A Kübler, Sandra
%Y Bhatia, Archna
%Y Bouma, Gosse
%Y Doğruöz, A. Seza
%Y Evang, Kilian
%Y Garcia, Marcos
%Y Giouli, Voula
%Y Han, Lifeng
%Y Nivre, Joakim
%Y Rademaker, Alexandre
%S Proceedings of the Joint Workshop on Multiword Expressions and Universal Dependencies (MWE-UD) @ LREC-COLING 2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F striebel-etal-2024-domain
%X In neural dependency parsing, as well as in the broader field of NLP, domain adaptation remains a challenging problem. When adapting a parser to a target domain, there is a fundamental tension between the need to make use of out-of-domain data and the need to ensure that syntactic characteristic of the target domain are learned. In this work we explore a way to balance these two competing concerns, namely using domain-weighted batch sampling, which allows us to use all available training data, while controlling the probability of sampling in- and out-of-domain data when constructing training batches. We conduct experiments using ten natural language domains and find that domain-weighted batch sampling yields substantial performance improvements in all ten domains compared to a baseline of conventional randomized batch sampling.
%U https://aclanthology.org/2024.mwe-1.24
%P 198-206
Markdown (Informal)
[Domain-Weighted Batch Sampling for Neural Dependency Parsing](https://aclanthology.org/2024.mwe-1.24) (Striebel et al., MWE-UDW-WS 2024)
ACL