@inproceedings{lai-etal-2024-camal,
title = "{CAMAL}: A Novel Dataset for Multi-label Conversational Argument Move Analysis",
author = "Lai, Viet Dac and
Pham, Duy Ngoc and
Steinberg, Jonathan and
Mikeska, Jamie and
Nguyen, Thien Huu",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.239",
pages = "2673--2682",
abstract = "Understanding the discussion moves that teachers and students use to engage in classroom discussions is important to support pre-service teacher learning and teacher educators. This work introduces a novel conversational multi-label corpus of teaching transcripts collected from a simulated classroom environment for Conversational Argument Move AnaLysis (CAMAL). The dataset offers various argumentation moves used by pre-service teachers and students in mathematics and science classroom discussions. The dataset includes 165 transcripts from these discussions that pre-service elementary teachers facilitated in a simulated classroom environment of five student avatars. The discussion transcripts were annotated by education assessment experts for nine argumentation moves (aka. intents) used by the pre-service teachers and students during the discussions. In this paper, we describe the dataset, our annotation framework, and the models we employed to detect argumentation moves. Our experiments with state-of-the-art models demonstrate the complexity of the CAMAL task presented in the dataset. The result reveals that models that combined CNN and LSTM structures with speaker ID graphs improved the F1-score of our baseline models to detect speakers{'} intents by a large margin. Given the complexity of the CAMAL task, it creates research opportunities for future studies. We share the dataset, the source code, and the annotation framework publicly at http://github.com/uonlp/camal-dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lai-etal-2024-camal">
<titleInfo>
<title>CAMAL: A Novel Dataset for Multi-label Conversational Argument Move Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Viet</namePart>
<namePart type="given">Dac</namePart>
<namePart type="family">Lai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Duy</namePart>
<namePart type="given">Ngoc</namePart>
<namePart type="family">Pham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Steinberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jamie</namePart>
<namePart type="family">Mikeska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thien</namePart>
<namePart type="given">Huu</namePart>
<namePart type="family">Nguyen</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 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</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>Understanding the discussion moves that teachers and students use to engage in classroom discussions is important to support pre-service teacher learning and teacher educators. This work introduces a novel conversational multi-label corpus of teaching transcripts collected from a simulated classroom environment for Conversational Argument Move AnaLysis (CAMAL). The dataset offers various argumentation moves used by pre-service teachers and students in mathematics and science classroom discussions. The dataset includes 165 transcripts from these discussions that pre-service elementary teachers facilitated in a simulated classroom environment of five student avatars. The discussion transcripts were annotated by education assessment experts for nine argumentation moves (aka. intents) used by the pre-service teachers and students during the discussions. In this paper, we describe the dataset, our annotation framework, and the models we employed to detect argumentation moves. Our experiments with state-of-the-art models demonstrate the complexity of the CAMAL task presented in the dataset. The result reveals that models that combined CNN and LSTM structures with speaker ID graphs improved the F1-score of our baseline models to detect speakers’ intents by a large margin. Given the complexity of the CAMAL task, it creates research opportunities for future studies. We share the dataset, the source code, and the annotation framework publicly at http://github.com/uonlp/camal-dataset.</abstract>
<identifier type="citekey">lai-etal-2024-camal</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.239</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>2673</start>
<end>2682</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CAMAL: A Novel Dataset for Multi-label Conversational Argument Move Analysis
%A Lai, Viet Dac
%A Pham, Duy Ngoc
%A Steinberg, Jonathan
%A Mikeska, Jamie
%A Nguyen, Thien Huu
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F lai-etal-2024-camal
%X Understanding the discussion moves that teachers and students use to engage in classroom discussions is important to support pre-service teacher learning and teacher educators. This work introduces a novel conversational multi-label corpus of teaching transcripts collected from a simulated classroom environment for Conversational Argument Move AnaLysis (CAMAL). The dataset offers various argumentation moves used by pre-service teachers and students in mathematics and science classroom discussions. The dataset includes 165 transcripts from these discussions that pre-service elementary teachers facilitated in a simulated classroom environment of five student avatars. The discussion transcripts were annotated by education assessment experts for nine argumentation moves (aka. intents) used by the pre-service teachers and students during the discussions. In this paper, we describe the dataset, our annotation framework, and the models we employed to detect argumentation moves. Our experiments with state-of-the-art models demonstrate the complexity of the CAMAL task presented in the dataset. The result reveals that models that combined CNN and LSTM structures with speaker ID graphs improved the F1-score of our baseline models to detect speakers’ intents by a large margin. Given the complexity of the CAMAL task, it creates research opportunities for future studies. We share the dataset, the source code, and the annotation framework publicly at http://github.com/uonlp/camal-dataset.
%U https://aclanthology.org/2024.lrec-main.239
%P 2673-2682
Markdown (Informal)
[CAMAL: A Novel Dataset for Multi-label Conversational Argument Move Analysis](https://aclanthology.org/2024.lrec-main.239) (Lai et al., LREC-COLING 2024)
ACL