@inproceedings{dhanwal-etal-2020-annotated,
title = "An Annotated Dataset of Discourse Modes in {H}indi Stories",
author = "Dhanwal, Swapnil and
Dutta, Hritwik and
Nankani, Hitesh and
Shrivastava, Nilay and
Kumar, Yaman and
Li, Junyi Jessy and
Mahata, Debanjan and
Gosangi, Rakesh and
Zhang, Haimin and
Shah, Rajiv Ratn and
Stent, Amanda",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.149",
pages = "1191--1196",
abstract = "In this paper, we present a new corpus consisting of sentences from Hindi short stories annotated for five different discourse modes argumentative, narrative, descriptive, dialogic and informative. We present a detailed account of the entire data collection and annotation processes. The annotations have a very high inter-annotator agreement (0.87 k-alpha). We analyze the data in terms of label distributions, part of speech tags, and sentence lengths. We characterize the performance of various classification algorithms on this dataset and perform ablation studies to understand the nature of the linguistic models suitable for capturing the nuances of the embedded discourse structures in the presented corpus.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dhanwal-etal-2020-annotated">
<titleInfo>
<title>An Annotated Dataset of Discourse Modes in Hindi Stories</title>
</titleInfo>
<name type="personal">
<namePart type="given">Swapnil</namePart>
<namePart type="family">Dhanwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hritwik</namePart>
<namePart type="family">Dutta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitesh</namePart>
<namePart type="family">Nankani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nilay</namePart>
<namePart type="family">Shrivastava</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaman</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junyi</namePart>
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debanjan</namePart>
<namePart type="family">Mahata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rakesh</namePart>
<namePart type="family">Gosangi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haimin</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rajiv</namePart>
<namePart type="given">Ratn</namePart>
<namePart type="family">Shah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amanda</namePart>
<namePart type="family">Stent</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</title>
</titleInfo>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>In this paper, we present a new corpus consisting of sentences from Hindi short stories annotated for five different discourse modes argumentative, narrative, descriptive, dialogic and informative. We present a detailed account of the entire data collection and annotation processes. The annotations have a very high inter-annotator agreement (0.87 k-alpha). We analyze the data in terms of label distributions, part of speech tags, and sentence lengths. We characterize the performance of various classification algorithms on this dataset and perform ablation studies to understand the nature of the linguistic models suitable for capturing the nuances of the embedded discourse structures in the presented corpus.</abstract>
<identifier type="citekey">dhanwal-etal-2020-annotated</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.149</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>1191</start>
<end>1196</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Annotated Dataset of Discourse Modes in Hindi Stories
%A Dhanwal, Swapnil
%A Dutta, Hritwik
%A Nankani, Hitesh
%A Shrivastava, Nilay
%A Kumar, Yaman
%A Li, Junyi Jessy
%A Mahata, Debanjan
%A Gosangi, Rakesh
%A Zhang, Haimin
%A Shah, Rajiv Ratn
%A Stent, Amanda
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F dhanwal-etal-2020-annotated
%X In this paper, we present a new corpus consisting of sentences from Hindi short stories annotated for five different discourse modes argumentative, narrative, descriptive, dialogic and informative. We present a detailed account of the entire data collection and annotation processes. The annotations have a very high inter-annotator agreement (0.87 k-alpha). We analyze the data in terms of label distributions, part of speech tags, and sentence lengths. We characterize the performance of various classification algorithms on this dataset and perform ablation studies to understand the nature of the linguistic models suitable for capturing the nuances of the embedded discourse structures in the presented corpus.
%U https://aclanthology.org/2020.lrec-1.149
%P 1191-1196
Markdown (Informal)
[An Annotated Dataset of Discourse Modes in Hindi Stories](https://aclanthology.org/2020.lrec-1.149) (Dhanwal et al., LREC 2020)
ACL
- Swapnil Dhanwal, Hritwik Dutta, Hitesh Nankani, Nilay Shrivastava, Yaman Kumar, Junyi Jessy Li, Debanjan Mahata, Rakesh Gosangi, Haimin Zhang, Rajiv Ratn Shah, and Amanda Stent. 2020. An Annotated Dataset of Discourse Modes in Hindi Stories. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 1191–1196, Marseille, France. European Language Resources Association.