<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chapuis-etal-2020-hierarchical">
    <titleInfo>
        <title>Hierarchical Pre-training for Sequence Labelling in Spoken Dialog</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Emile</namePart>
        <namePart type="family">Chapuis</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Pierre</namePart>
        <namePart type="family">Colombo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Matteo</namePart>
        <namePart type="family">Manica</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Matthieu</namePart>
        <namePart type="family">Labeau</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chloé</namePart>
        <namePart type="family">Clavel</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Trevor</namePart>
            <namePart type="family">Cohn</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yulan</namePart>
            <namePart type="family">He</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yang</namePart>
            <namePart type="family">Liu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Sequence labelling tasks like Dialog Act and Emotion/Sentiment identification are a key component of spoken dialog systems. In this work, we propose a new approach to learn generic representations adapted to spoken dialog, which we evaluate on a new benchmark we call Sequence labellIng evaLuatIon benChmark fOr spoken laNguagE benchmark (SILICONE). SILICONE is model-agnostic and contains 10 different datasets of various sizes. We obtain our representations with a hierarchical encoder based on transformer architectures, for which we extend two well-known pre-training objectives. Pre-training is performed on OpenSubtitles: a large corpus of spoken dialog containing over 2.3 billion of tokens. We demonstrate how hierarchical encoders achieve competitive results with consistently fewer parameters compared to state-of-the-art models and we show their importance for both pre-training and fine-tuning.</abstract>
    <identifier type="citekey">chapuis-etal-2020-hierarchical</identifier>
    <identifier type="doi">10.18653/v1/2020.findings-emnlp.239</identifier>
    <location>
        <url>https://aclanthology.org/2020.findings-emnlp.239</url>
    </location>
    <part>
        <date>2020-11</date>
        <extent unit="page">
            <start>2636</start>
            <end>2648</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Hierarchical Pre-training for Sequence Labelling in Spoken Dialog
%A Chapuis, Emile
%A Colombo, Pierre
%A Manica, Matteo
%A Labeau, Matthieu
%A Clavel, Chloé
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F chapuis-etal-2020-hierarchical
%X Sequence labelling tasks like Dialog Act and Emotion/Sentiment identification are a key component of spoken dialog systems. In this work, we propose a new approach to learn generic representations adapted to spoken dialog, which we evaluate on a new benchmark we call Sequence labellIng evaLuatIon benChmark fOr spoken laNguagE benchmark (SILICONE). SILICONE is model-agnostic and contains 10 different datasets of various sizes. We obtain our representations with a hierarchical encoder based on transformer architectures, for which we extend two well-known pre-training objectives. Pre-training is performed on OpenSubtitles: a large corpus of spoken dialog containing over 2.3 billion of tokens. We demonstrate how hierarchical encoders achieve competitive results with consistently fewer parameters compared to state-of-the-art models and we show their importance for both pre-training and fine-tuning.
%R 10.18653/v1/2020.findings-emnlp.239
%U https://aclanthology.org/2020.findings-emnlp.239
%U https://doi.org/10.18653/v1/2020.findings-emnlp.239
%P 2636-2648

Markdown (Informal)

[Hierarchical Pre-training for Sequence Labelling in Spoken Dialog](https://aclanthology.org/2020.findings-emnlp.239) (Chapuis et al., Findings 2020)

• Hierarchical Pre-training for Sequence Labelling in Spoken Dialog (Chapuis et al., Findings 2020)

ACL

• Emile Chapuis, Pierre Colombo, Matteo Manica, Matthieu Labeau, and Chloé Clavel. 2020. Hierarchical Pre-training for Sequence Labelling in Spoken Dialog. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 2636–2648, Online. Association for Computational Linguistics.