@inproceedings{bojic-etal-2026-coachlah,
title = "{C}oach{L}ah: A {S}inglish{--}{E}nglish Parallel Corpus of Health Coaching Conversations with Behavior Goal Annotations",
author = "Bojic, Iva and
Ravaut, Mathieu and
Ma, Stephanie Hilary Xinyi and
Tan, Doreen and
Ho, Andy Hau Yan and
Khong, Andy",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.3/",
doi = "10.63317/54des2aenesc",
pages = "35--49",
abstract = "Health coaching (HC) aims to promote sustainable behavior change through goal-oriented dialogue, but research in this area is limited by the scarcity of authentic, transcript-based corpora. Existing datasets are small, English-only, and Western-centric, overlooking cultural and linguistic factors that shape real-world HC interactions. We introduce CoachLah, the first Singlish{--}English parallel corpus of HC conversations collected from a randomized controlled trial in Singapore. The dataset comprises 36,852 utterances transcribed from almost 160 hours of recorded HC sessions with 51 clients and 4 professional health coaches. Each dialogue is speaker-labeled, transcribed in Singlish, and aligned with high-quality English translations to preserve linguistic and cultural nuances. All sessions include HC summaries written by health coaches after each HC session, from which behavioral goals were manually annotated. To demonstrate the dataset{'}s utility, we benchmark two downstream tasks: (i) Singlish-to-English translation using fine-tuned open-weight models (e.g., Gemma-2-9B-it) with Low-Rank Adaptation, and (ii) behavioral goal extraction from unstructured HC summaries using span-based modeling (e.g., DeBERTa-v3-base). Together, these contributions establish the first culturally grounded benchmark for low-resource, goal-oriented dialogue research in HC. Both the code and the dataset are available at: \url{https://github.com/IvaBojic/CoachLah}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bojic-etal-2026-coachlah">
<titleInfo>
<title>CoachLah: A Singlish–English Parallel Corpus of Health Coaching Conversations with Behavior Goal Annotations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iva</namePart>
<namePart type="family">Bojic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mathieu</namePart>
<namePart type="family">Ravaut</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephanie</namePart>
<namePart type="given">Hilary</namePart>
<namePart type="given">Xinyi</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Doreen</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andy</namePart>
<namePart type="given">Hau</namePart>
<namePart type="given">Yan</namePart>
<namePart type="family">Ho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andy</namePart>
<namePart type="family">Khong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Health coaching (HC) aims to promote sustainable behavior change through goal-oriented dialogue, but research in this area is limited by the scarcity of authentic, transcript-based corpora. Existing datasets are small, English-only, and Western-centric, overlooking cultural and linguistic factors that shape real-world HC interactions. We introduce CoachLah, the first Singlish–English parallel corpus of HC conversations collected from a randomized controlled trial in Singapore. The dataset comprises 36,852 utterances transcribed from almost 160 hours of recorded HC sessions with 51 clients and 4 professional health coaches. Each dialogue is speaker-labeled, transcribed in Singlish, and aligned with high-quality English translations to preserve linguistic and cultural nuances. All sessions include HC summaries written by health coaches after each HC session, from which behavioral goals were manually annotated. To demonstrate the dataset’s utility, we benchmark two downstream tasks: (i) Singlish-to-English translation using fine-tuned open-weight models (e.g., Gemma-2-9B-it) with Low-Rank Adaptation, and (ii) behavioral goal extraction from unstructured HC summaries using span-based modeling (e.g., DeBERTa-v3-base). Together, these contributions establish the first culturally grounded benchmark for low-resource, goal-oriented dialogue research in HC. Both the code and the dataset are available at: https://github.com/IvaBojic/CoachLah.</abstract>
<identifier type="citekey">bojic-etal-2026-coachlah</identifier>
<identifier type="doi">10.63317/54des2aenesc</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.3/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>35</start>
<end>49</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CoachLah: A Singlish–English Parallel Corpus of Health Coaching Conversations with Behavior Goal Annotations
%A Bojic, Iva
%A Ravaut, Mathieu
%A Ma, Stephanie Hilary Xinyi
%A Tan, Doreen
%A Ho, Andy Hau Yan
%A Khong, Andy
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F bojic-etal-2026-coachlah
%X Health coaching (HC) aims to promote sustainable behavior change through goal-oriented dialogue, but research in this area is limited by the scarcity of authentic, transcript-based corpora. Existing datasets are small, English-only, and Western-centric, overlooking cultural and linguistic factors that shape real-world HC interactions. We introduce CoachLah, the first Singlish–English parallel corpus of HC conversations collected from a randomized controlled trial in Singapore. The dataset comprises 36,852 utterances transcribed from almost 160 hours of recorded HC sessions with 51 clients and 4 professional health coaches. Each dialogue is speaker-labeled, transcribed in Singlish, and aligned with high-quality English translations to preserve linguistic and cultural nuances. All sessions include HC summaries written by health coaches after each HC session, from which behavioral goals were manually annotated. To demonstrate the dataset’s utility, we benchmark two downstream tasks: (i) Singlish-to-English translation using fine-tuned open-weight models (e.g., Gemma-2-9B-it) with Low-Rank Adaptation, and (ii) behavioral goal extraction from unstructured HC summaries using span-based modeling (e.g., DeBERTa-v3-base). Together, these contributions establish the first culturally grounded benchmark for low-resource, goal-oriented dialogue research in HC. Both the code and the dataset are available at: https://github.com/IvaBojic/CoachLah.
%R 10.63317/54des2aenesc
%U https://aclanthology.org/2026.lrec-1.3/
%U https://doi.org/10.63317/54des2aenesc
%P 35-49
Markdown (Informal)
[CoachLah: A Singlish–English Parallel Corpus of Health Coaching Conversations with Behavior Goal Annotations](https://aclanthology.org/2026.lrec-1.3/) (Bojic et al., LREC 2026)
ACL