<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2023-discourse">
    <titleInfo>
        <title>Discourse Structure Extraction from Pre-Trained and Fine-Tuned Language Models in Dialogues</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Chuyuan</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Patrick</namePart>
        <namePart type="family">Huber</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wen</namePart>
        <namePart type="family">Xiao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Maxime</namePart>
        <namePart type="family">Amblard</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chloe</namePart>
        <namePart type="family">Braud</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Giuseppe</namePart>
        <namePart type="family">Carenini</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EACL 2023</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Andreas</namePart>
            <namePart type="family">Vlachos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Isabelle</namePart>
            <namePart type="family">Augenstein</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Dubrovnik, Croatia</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Discourse processing suffers from data sparsity, especially for dialogues. As a result, we explore approaches to infer latent discourse structures for dialogues, based on attention matrices from Pre-trained Language Models (PLMs). We investigate multiple auxiliary tasks for fine-tuning and show that the dialogue-tailored Sentence Ordering task performs best. To locate and exploit discourse information in PLMs, we propose an unsupervised and a semi-supervised method. Our proposals thereby achieve encouraging results on the STAC corpus, with F1 scores of 57.2 and 59.3 for the unsupervised and semi-supervised methods, respectively. When restricted to projective trees, our scores improved to 63.3 and 68.1.</abstract>
    <identifier type="citekey">li-etal-2023-discourse</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-eacl.194</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-eacl.194/</url>
    </location>
    <part>
        <date>2023-05</date>
        <extent unit="page">
            <start>2562</start>
            <end>2579</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Discourse Structure Extraction from Pre-Trained and Fine-Tuned Language Models in Dialogues
%A Li, Chuyuan
%A Huber, Patrick
%A Xiao, Wen
%A Amblard, Maxime
%A Braud, Chloe
%A Carenini, Giuseppe
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Findings of the Association for Computational Linguistics: EACL 2023
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F li-etal-2023-discourse
%X Discourse processing suffers from data sparsity, especially for dialogues. As a result, we explore approaches to infer latent discourse structures for dialogues, based on attention matrices from Pre-trained Language Models (PLMs). We investigate multiple auxiliary tasks for fine-tuning and show that the dialogue-tailored Sentence Ordering task performs best. To locate and exploit discourse information in PLMs, we propose an unsupervised and a semi-supervised method. Our proposals thereby achieve encouraging results on the STAC corpus, with F1 scores of 57.2 and 59.3 for the unsupervised and semi-supervised methods, respectively. When restricted to projective trees, our scores improved to 63.3 and 68.1.
%R 10.18653/v1/2023.findings-eacl.194
%U https://aclanthology.org/2023.findings-eacl.194/
%U https://doi.org/10.18653/v1/2023.findings-eacl.194
%P 2562-2579

Markdown (Informal)

[Discourse Structure Extraction from Pre-Trained and Fine-Tuned Language Models in Dialogues](https://aclanthology.org/2023.findings-eacl.194/) (Li et al., Findings 2023)

• Discourse Structure Extraction from Pre-Trained and Fine-Tuned Language Models in Dialogues (Li et al., Findings 2023)

ACL

• Chuyuan Li, Patrick Huber, Wen Xiao, Maxime Amblard, Chloe Braud, and Giuseppe Carenini. 2023. Discourse Structure Extraction from Pre-Trained and Fine-Tuned Language Models in Dialogues. In Findings of the Association for Computational Linguistics: EACL 2023, pages 2562–2579, Dubrovnik, Croatia. Association for Computational Linguistics.