@inproceedings{aycock-bawden-2024-topic,
title = "Topic-guided Example Selection for Domain Adaptation in {LLM}-based Machine Translation",
author = "Aycock, Seth and
Bawden, Rachel",
editor = "Falk, Neele and
Papi, Sara and
Zhang, Mike",
booktitle = "Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop",
month = mar,
year = "2024",
address = "St. Julian{'}s, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.eacl-srw.13",
pages = "175--195",
abstract = "Current machine translation (MT) systems perform well in the domains on which they were trained, but adaptation to unseen domains remains a challenge. Rather than fine-tuning on domain data or modifying the architecture for training, an alternative approach exploits large language models (LLMs), which are performant across NLP tasks especially when presented with in-context examples. We focus on adapting a pre-trained LLM to a domain at inference through in-context example selection. For MT, examples are usually randomly selected from a development set. Some more recent methods though select using the more intuitive basis of test source similarity. We employ topic models to select examples based on abstract semantic relationships below the level of a domain. We test the relevance of these statistical models and use them to select informative examples even for out-of-domain inputs, experimenting on 7 diverse domains and 11 language pairs of differing resourcedness. Our method outperforms baselines on challenging multilingual out-of-domain tests, though it does not match performance with strong baselines for the in-language setting. We find that adding few-shot examples and related keywords consistently improves translation quality, that example diversity must be balanced with source similarity, and that our pipeline is overly restrictive for example selection when a targeted development set is available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aycock-bawden-2024-topic">
<titleInfo>
<title>Topic-guided Example Selection for Domain Adaptation in LLM-based Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Seth</namePart>
<namePart type="family">Aycock</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachel</namePart>
<namePart type="family">Bawden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Neele</namePart>
<namePart type="family">Falk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Papi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julian’s, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Current machine translation (MT) systems perform well in the domains on which they were trained, but adaptation to unseen domains remains a challenge. Rather than fine-tuning on domain data or modifying the architecture for training, an alternative approach exploits large language models (LLMs), which are performant across NLP tasks especially when presented with in-context examples. We focus on adapting a pre-trained LLM to a domain at inference through in-context example selection. For MT, examples are usually randomly selected from a development set. Some more recent methods though select using the more intuitive basis of test source similarity. We employ topic models to select examples based on abstract semantic relationships below the level of a domain. We test the relevance of these statistical models and use them to select informative examples even for out-of-domain inputs, experimenting on 7 diverse domains and 11 language pairs of differing resourcedness. Our method outperforms baselines on challenging multilingual out-of-domain tests, though it does not match performance with strong baselines for the in-language setting. We find that adding few-shot examples and related keywords consistently improves translation quality, that example diversity must be balanced with source similarity, and that our pipeline is overly restrictive for example selection when a targeted development set is available.</abstract>
<identifier type="citekey">aycock-bawden-2024-topic</identifier>
<location>
<url>https://aclanthology.org/2024.eacl-srw.13</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>175</start>
<end>195</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Topic-guided Example Selection for Domain Adaptation in LLM-based Machine Translation
%A Aycock, Seth
%A Bawden, Rachel
%Y Falk, Neele
%Y Papi, Sara
%Y Zhang, Mike
%S Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F aycock-bawden-2024-topic
%X Current machine translation (MT) systems perform well in the domains on which they were trained, but adaptation to unseen domains remains a challenge. Rather than fine-tuning on domain data or modifying the architecture for training, an alternative approach exploits large language models (LLMs), which are performant across NLP tasks especially when presented with in-context examples. We focus on adapting a pre-trained LLM to a domain at inference through in-context example selection. For MT, examples are usually randomly selected from a development set. Some more recent methods though select using the more intuitive basis of test source similarity. We employ topic models to select examples based on abstract semantic relationships below the level of a domain. We test the relevance of these statistical models and use them to select informative examples even for out-of-domain inputs, experimenting on 7 diverse domains and 11 language pairs of differing resourcedness. Our method outperforms baselines on challenging multilingual out-of-domain tests, though it does not match performance with strong baselines for the in-language setting. We find that adding few-shot examples and related keywords consistently improves translation quality, that example diversity must be balanced with source similarity, and that our pipeline is overly restrictive for example selection when a targeted development set is available.
%U https://aclanthology.org/2024.eacl-srw.13
%P 175-195
Markdown (Informal)
[Topic-guided Example Selection for Domain Adaptation in LLM-based Machine Translation](https://aclanthology.org/2024.eacl-srw.13) (Aycock & Bawden, EACL 2024)
ACL