@inproceedings{taniguchi-etal-2020-large,
title = "A Large-Scale Corpus of {E}-mail Conversations with Standard and Two-Level Dialogue Act Annotations",
author = "Taniguchi, Motoki and
Ueda, Yoshihiro and
Taniguchi, Tomoki and
Ohkuma, Tomoko",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.436",
doi = "10.18653/v1/2020.coling-main.436",
pages = "4969--4980",
abstract = "We present a large-scale corpus of e-mail conversations with domain-agnostic and two-level dialogue act (DA) annotations towards the goal of a better understanding of asynchronous conversations. We annotate over 6,000 messages and 35,000 sentences from more than 2,000 threads. For a domain-independent and application-independent DA annotations, we choose ISO standard 24617-2 as the annotation scheme. To assess the difficulty of DA recognition on our corpus, we evaluate several models, including a pre-trained contextual representation model, as our baselines. The experimental results show that BERT outperforms other neural network models, including previous state-of-the-art models, but falls short of a human performance. We also demonstrate that DA tags of two-level granularity enable a DA recognition model to learn efficiently by using multi-task learning. An evaluation of a model trained on our corpus against other domains of asynchronous conversation reveals the domain independence of our DA annotations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="taniguchi-etal-2020-large">
<titleInfo>
<title>A Large-Scale Corpus of E-mail Conversations with Standard and Two-Level Dialogue Act Annotations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Motoki</namePart>
<namePart type="family">Taniguchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoshihiro</namePart>
<namePart type="family">Ueda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomoki</namePart>
<namePart type="family">Taniguchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomoko</namePart>
<namePart type="family">Ohkuma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a large-scale corpus of e-mail conversations with domain-agnostic and two-level dialogue act (DA) annotations towards the goal of a better understanding of asynchronous conversations. We annotate over 6,000 messages and 35,000 sentences from more than 2,000 threads. For a domain-independent and application-independent DA annotations, we choose ISO standard 24617-2 as the annotation scheme. To assess the difficulty of DA recognition on our corpus, we evaluate several models, including a pre-trained contextual representation model, as our baselines. The experimental results show that BERT outperforms other neural network models, including previous state-of-the-art models, but falls short of a human performance. We also demonstrate that DA tags of two-level granularity enable a DA recognition model to learn efficiently by using multi-task learning. An evaluation of a model trained on our corpus against other domains of asynchronous conversation reveals the domain independence of our DA annotations.</abstract>
<identifier type="citekey">taniguchi-etal-2020-large</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.436</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.436</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>4969</start>
<end>4980</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Large-Scale Corpus of E-mail Conversations with Standard and Two-Level Dialogue Act Annotations
%A Taniguchi, Motoki
%A Ueda, Yoshihiro
%A Taniguchi, Tomoki
%A Ohkuma, Tomoko
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F taniguchi-etal-2020-large
%X We present a large-scale corpus of e-mail conversations with domain-agnostic and two-level dialogue act (DA) annotations towards the goal of a better understanding of asynchronous conversations. We annotate over 6,000 messages and 35,000 sentences from more than 2,000 threads. For a domain-independent and application-independent DA annotations, we choose ISO standard 24617-2 as the annotation scheme. To assess the difficulty of DA recognition on our corpus, we evaluate several models, including a pre-trained contextual representation model, as our baselines. The experimental results show that BERT outperforms other neural network models, including previous state-of-the-art models, but falls short of a human performance. We also demonstrate that DA tags of two-level granularity enable a DA recognition model to learn efficiently by using multi-task learning. An evaluation of a model trained on our corpus against other domains of asynchronous conversation reveals the domain independence of our DA annotations.
%R 10.18653/v1/2020.coling-main.436
%U https://aclanthology.org/2020.coling-main.436
%U https://doi.org/10.18653/v1/2020.coling-main.436
%P 4969-4980
Markdown (Informal)
[A Large-Scale Corpus of E-mail Conversations with Standard and Two-Level Dialogue Act Annotations](https://aclanthology.org/2020.coling-main.436) (Taniguchi et al., COLING 2020)
ACL