@inproceedings{pombal-etal-2024-improving,
title = "Improving Context Usage for Translating Bilingual Customer Support Chat with Large Language Models",
author = "Pombal, Jose and
Agrawal, Sweta and
Martins, Andr{\'e}",
editor = "Haddow, Barry and
Kocmi, Tom and
Koehn, Philipp and
Monz, Christof",
booktitle = "Proceedings of the Ninth Conference on Machine Translation",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.wmt-1.100",
pages = "993--1003",
abstract = "This paper describes Unbabel+IT{'}s submission to the Chat Shared Task held at the Workshop of Machine Translation 2024. The task focuses on translating customer support chats between agents and customers communicating in different languages. We present two strategies for adapting state-of-the-art language models to better utilize contextual information when translating such conversations. Our training strategy involves finetuning the model on chat datasets with context-augmented instructions, resulting in a specialized model, TOWERCHAT. For inference, we propose a novel quality-aware decoding approach that leverages a context-aware metric, CONTEXTCOMET, to select the optimal translation from a pool of candidates. We evaluate our proposed approach on the official shared task datasets for ten language pairs, showing that our submission consistently outperforms baselines on all and competing systems on 8 out of 10 language pairs across multiple automated metrics. Remarkably, TOWERCHAT outperforms our contrastive submission based on the much larger TOWER-V2-70B model while being 10{\mbox{$\times$}} smaller. According to human evaluation, our system outperforms all other systems and baselines across all language pairs. These results underscore the importance of context-aware training and inference in handling complex bilingual dialogues.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pombal-etal-2024-improving">
<titleInfo>
<title>Improving Context Usage for Translating Bilingual Customer Support Chat with Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jose</namePart>
<namePart type="family">Pombal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sweta</namePart>
<namePart type="family">Agrawal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">André</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth Conference on Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Barry</namePart>
<namePart type="family">Haddow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Kocmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Koehn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christof</namePart>
<namePart type="family">Monz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes Unbabel+IT’s submission to the Chat Shared Task held at the Workshop of Machine Translation 2024. The task focuses on translating customer support chats between agents and customers communicating in different languages. We present two strategies for adapting state-of-the-art language models to better utilize contextual information when translating such conversations. Our training strategy involves finetuning the model on chat datasets with context-augmented instructions, resulting in a specialized model, TOWERCHAT. For inference, we propose a novel quality-aware decoding approach that leverages a context-aware metric, CONTEXTCOMET, to select the optimal translation from a pool of candidates. We evaluate our proposed approach on the official shared task datasets for ten language pairs, showing that our submission consistently outperforms baselines on all and competing systems on 8 out of 10 language pairs across multiple automated metrics. Remarkably, TOWERCHAT outperforms our contrastive submission based on the much larger TOWER-V2-70B model while being 10\times smaller. According to human evaluation, our system outperforms all other systems and baselines across all language pairs. These results underscore the importance of context-aware training and inference in handling complex bilingual dialogues.</abstract>
<identifier type="citekey">pombal-etal-2024-improving</identifier>
<location>
<url>https://aclanthology.org/2024.wmt-1.100</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>993</start>
<end>1003</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Context Usage for Translating Bilingual Customer Support Chat with Large Language Models
%A Pombal, Jose
%A Agrawal, Sweta
%A Martins, André
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Koehn, Philipp
%Y Monz, Christof
%S Proceedings of the Ninth Conference on Machine Translation
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F pombal-etal-2024-improving
%X This paper describes Unbabel+IT’s submission to the Chat Shared Task held at the Workshop of Machine Translation 2024. The task focuses on translating customer support chats between agents and customers communicating in different languages. We present two strategies for adapting state-of-the-art language models to better utilize contextual information when translating such conversations. Our training strategy involves finetuning the model on chat datasets with context-augmented instructions, resulting in a specialized model, TOWERCHAT. For inference, we propose a novel quality-aware decoding approach that leverages a context-aware metric, CONTEXTCOMET, to select the optimal translation from a pool of candidates. We evaluate our proposed approach on the official shared task datasets for ten language pairs, showing that our submission consistently outperforms baselines on all and competing systems on 8 out of 10 language pairs across multiple automated metrics. Remarkably, TOWERCHAT outperforms our contrastive submission based on the much larger TOWER-V2-70B model while being 10\times smaller. According to human evaluation, our system outperforms all other systems and baselines across all language pairs. These results underscore the importance of context-aware training and inference in handling complex bilingual dialogues.
%U https://aclanthology.org/2024.wmt-1.100
%P 993-1003
Markdown (Informal)
[Improving Context Usage for Translating Bilingual Customer Support Chat with Large Language Models](https://aclanthology.org/2024.wmt-1.100) (Pombal et al., WMT 2024)
ACL