@inproceedings{ekstedt-skantze-2020-turngpt,
title = "{T}urn{GPT}: a Transformer-based Language Model for Predicting Turn-taking in Spoken Dialog",
author = "Ekstedt, Erik and
Skantze, Gabriel",
editor = "Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.findings-emnlp.268",
doi = "10.18653/v1/2020.findings-emnlp.268",
pages = "2981--2990",
abstract = "Syntactic and pragmatic completeness is known to be important for turn-taking prediction, but so far machine learning models of turn-taking have used such linguistic information in a limited way. In this paper, we introduce TurnGPT, a transformer-based language model for predicting turn-shifts in spoken dialog. The model has been trained and evaluated on a variety of written and spoken dialog datasets. We show that the model outperforms two baselines used in prior work. We also report on an ablation study, as well as attention and gradient analyses, which show that the model is able to utilize the dialog context and pragmatic completeness for turn-taking prediction. Finally, we explore the model{'}s potential in not only detecting, but also projecting, turn-completions.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ekstedt-skantze-2020-turngpt">
<titleInfo>
<title>TurnGPT: a Transformer-based Language Model for Predicting Turn-taking in Spoken Dialog</title>
</titleInfo>
<name type="personal">
<namePart type="given">Erik</namePart>
<namePart type="family">Ekstedt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Skantze</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>Syntactic and pragmatic completeness is known to be important for turn-taking prediction, but so far machine learning models of turn-taking have used such linguistic information in a limited way. In this paper, we introduce TurnGPT, a transformer-based language model for predicting turn-shifts in spoken dialog. The model has been trained and evaluated on a variety of written and spoken dialog datasets. We show that the model outperforms two baselines used in prior work. We also report on an ablation study, as well as attention and gradient analyses, which show that the model is able to utilize the dialog context and pragmatic completeness for turn-taking prediction. Finally, we explore the model’s potential in not only detecting, but also projecting, turn-completions.</abstract>
<identifier type="citekey">ekstedt-skantze-2020-turngpt</identifier>
<identifier type="doi">10.18653/v1/2020.findings-emnlp.268</identifier>
<location>
<url>https://aclanthology.org/2020.findings-emnlp.268</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>2981</start>
<end>2990</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TurnGPT: a Transformer-based Language Model for Predicting Turn-taking in Spoken Dialog
%A Ekstedt, Erik
%A Skantze, Gabriel
%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 ekstedt-skantze-2020-turngpt
%X Syntactic and pragmatic completeness is known to be important for turn-taking prediction, but so far machine learning models of turn-taking have used such linguistic information in a limited way. In this paper, we introduce TurnGPT, a transformer-based language model for predicting turn-shifts in spoken dialog. The model has been trained and evaluated on a variety of written and spoken dialog datasets. We show that the model outperforms two baselines used in prior work. We also report on an ablation study, as well as attention and gradient analyses, which show that the model is able to utilize the dialog context and pragmatic completeness for turn-taking prediction. Finally, we explore the model’s potential in not only detecting, but also projecting, turn-completions.
%R 10.18653/v1/2020.findings-emnlp.268
%U https://aclanthology.org/2020.findings-emnlp.268
%U https://doi.org/10.18653/v1/2020.findings-emnlp.268
%P 2981-2990
Markdown (Informal)
[TurnGPT: a Transformer-based Language Model for Predicting Turn-taking in Spoken Dialog](https://aclanthology.org/2020.findings-emnlp.268) (Ekstedt & Skantze, Findings 2020)
ACL