@inproceedings{medina-grespan-etal-2023-logic,
title = "Logic-driven Indirect Supervision: An Application to Crisis Counseling",
author = "Medina Grespan, Mattia and
Broadbent, Meghan and
Zhang, Xinyao and
Axford, Katherine and
Kious, Brent and
Imel, Zac and
Srikumar, Vivek",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.654",
doi = "10.18653/v1/2023.acl-long.654",
pages = "11704--11722",
abstract = "Ensuring the effectiveness of text-based crisis counseling requires observing ongoing conversations and providing feedback, both labor-intensive tasks. Automatic analysis of conversations{---}at the full chat and utterance levels{---}may help support counselors and provide better care. While some session-level training data (e.g., rating of patient risk) is often available from counselors, labeling utterances requires expensive post hoc annotation. But the latter can not only provide insights about conversation dynamics, but can also serve to support quality assurance efforts for counselors. In this paper, we examine if inexpensive{---}and potentially noisy{---}session-level annotation can help improve label utterances. To this end, we propose a logic-based indirect supervision approach that exploits declaratively stated structural dependencies between both levels of annotation to improve utterance modeling. We show that adding these rules gives an improvement of 3.5{\%} f-score over a strong multi-task baseline for utterance-level predictions. We demonstrate via ablation studies how indirect supervision via logic rules also improves the consistency and robustness of the system.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="medina-grespan-etal-2023-logic">
<titleInfo>
<title>Logic-driven Indirect Supervision: An Application to Crisis Counseling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mattia</namePart>
<namePart type="family">Medina Grespan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meghan</namePart>
<namePart type="family">Broadbent</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinyao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katherine</namePart>
<namePart type="family">Axford</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brent</namePart>
<namePart type="family">Kious</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zac</namePart>
<namePart type="family">Imel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Ensuring the effectiveness of text-based crisis counseling requires observing ongoing conversations and providing feedback, both labor-intensive tasks. Automatic analysis of conversations—at the full chat and utterance levels—may help support counselors and provide better care. While some session-level training data (e.g., rating of patient risk) is often available from counselors, labeling utterances requires expensive post hoc annotation. But the latter can not only provide insights about conversation dynamics, but can also serve to support quality assurance efforts for counselors. In this paper, we examine if inexpensive—and potentially noisy—session-level annotation can help improve label utterances. To this end, we propose a logic-based indirect supervision approach that exploits declaratively stated structural dependencies between both levels of annotation to improve utterance modeling. We show that adding these rules gives an improvement of 3.5% f-score over a strong multi-task baseline for utterance-level predictions. We demonstrate via ablation studies how indirect supervision via logic rules also improves the consistency and robustness of the system.</abstract>
<identifier type="citekey">medina-grespan-etal-2023-logic</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.654</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.654</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>11704</start>
<end>11722</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Logic-driven Indirect Supervision: An Application to Crisis Counseling
%A Medina Grespan, Mattia
%A Broadbent, Meghan
%A Zhang, Xinyao
%A Axford, Katherine
%A Kious, Brent
%A Imel, Zac
%A Srikumar, Vivek
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F medina-grespan-etal-2023-logic
%X Ensuring the effectiveness of text-based crisis counseling requires observing ongoing conversations and providing feedback, both labor-intensive tasks. Automatic analysis of conversations—at the full chat and utterance levels—may help support counselors and provide better care. While some session-level training data (e.g., rating of patient risk) is often available from counselors, labeling utterances requires expensive post hoc annotation. But the latter can not only provide insights about conversation dynamics, but can also serve to support quality assurance efforts for counselors. In this paper, we examine if inexpensive—and potentially noisy—session-level annotation can help improve label utterances. To this end, we propose a logic-based indirect supervision approach that exploits declaratively stated structural dependencies between both levels of annotation to improve utterance modeling. We show that adding these rules gives an improvement of 3.5% f-score over a strong multi-task baseline for utterance-level predictions. We demonstrate via ablation studies how indirect supervision via logic rules also improves the consistency and robustness of the system.
%R 10.18653/v1/2023.acl-long.654
%U https://aclanthology.org/2023.acl-long.654
%U https://doi.org/10.18653/v1/2023.acl-long.654
%P 11704-11722
Markdown (Informal)
[Logic-driven Indirect Supervision: An Application to Crisis Counseling](https://aclanthology.org/2023.acl-long.654) (Medina Grespan et al., ACL 2023)
ACL
- Mattia Medina Grespan, Meghan Broadbent, Xinyao Zhang, Katherine Axford, Brent Kious, Zac Imel, and Vivek Srikumar. 2023. Logic-driven Indirect Supervision: An Application to Crisis Counseling. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 11704–11722, Toronto, Canada. Association for Computational Linguistics.