@inproceedings{li-etal-2020-molweni,
title = "Molweni: A Challenge Multiparty Dialogues-based Machine Reading Comprehension Dataset with Discourse Structure",
author = "Li, Jiaqi and
Liu, Ming and
Kan, Min-Yen and
Zheng, Zihao and
Wang, Zekun and
Lei, Wenqiang and
Liu, Ting and
Qin, Bing",
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.238/",
doi = "10.18653/v1/2020.coling-main.238",
pages = "2642--2652",
abstract = "Research into the area of multiparty dialog has grown considerably over recent years. We present the Molweni dataset, a machine reading comprehension (MRC) dataset with discourse structure built over multiparty dialog. Molweni`s source samples from the Ubuntu Chat Corpus, including 10,000 dialogs comprising 88,303 utterances. We annotate 30,066 questions on this corpus, including both answerable and unanswerable questions. Molweni also uniquely contributes discourse dependency annotations in a modified Segmented Discourse Representation Theory (SDRT; Asher et al., 2016) style for all of its multiparty dialogs, contributing large-scale (78,245 annotated discourse relations) data to bear on the task of multiparty dialog discourse parsing. Our experiments show that Molweni is a challenging dataset for current MRC models: BERT-wwm, a current, strong SQuAD 2.0 performer, achieves only 67.7{\%} F1 on Molweni`s questions, a 20+{\%} significant drop as compared against its SQuAD 2.0 performance."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2020-molweni">
<titleInfo>
<title>Molweni: A Challenge Multiparty Dialogues-based Machine Reading Comprehension Dataset with Discourse Structure</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiaqi</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zihao</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zekun</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenqiang</namePart>
<namePart type="family">Lei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ting</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bing</namePart>
<namePart type="family">Qin</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>Research into the area of multiparty dialog has grown considerably over recent years. We present the Molweni dataset, a machine reading comprehension (MRC) dataset with discourse structure built over multiparty dialog. Molweni‘s source samples from the Ubuntu Chat Corpus, including 10,000 dialogs comprising 88,303 utterances. We annotate 30,066 questions on this corpus, including both answerable and unanswerable questions. Molweni also uniquely contributes discourse dependency annotations in a modified Segmented Discourse Representation Theory (SDRT; Asher et al., 2016) style for all of its multiparty dialogs, contributing large-scale (78,245 annotated discourse relations) data to bear on the task of multiparty dialog discourse parsing. Our experiments show that Molweni is a challenging dataset for current MRC models: BERT-wwm, a current, strong SQuAD 2.0 performer, achieves only 67.7% F1 on Molweni‘s questions, a 20+% significant drop as compared against its SQuAD 2.0 performance.</abstract>
<identifier type="citekey">li-etal-2020-molweni</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.238</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.238/</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>2642</start>
<end>2652</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Molweni: A Challenge Multiparty Dialogues-based Machine Reading Comprehension Dataset with Discourse Structure
%A Li, Jiaqi
%A Liu, Ming
%A Kan, Min-Yen
%A Zheng, Zihao
%A Wang, Zekun
%A Lei, Wenqiang
%A Liu, Ting
%A Qin, Bing
%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 li-etal-2020-molweni
%X Research into the area of multiparty dialog has grown considerably over recent years. We present the Molweni dataset, a machine reading comprehension (MRC) dataset with discourse structure built over multiparty dialog. Molweni‘s source samples from the Ubuntu Chat Corpus, including 10,000 dialogs comprising 88,303 utterances. We annotate 30,066 questions on this corpus, including both answerable and unanswerable questions. Molweni also uniquely contributes discourse dependency annotations in a modified Segmented Discourse Representation Theory (SDRT; Asher et al., 2016) style for all of its multiparty dialogs, contributing large-scale (78,245 annotated discourse relations) data to bear on the task of multiparty dialog discourse parsing. Our experiments show that Molweni is a challenging dataset for current MRC models: BERT-wwm, a current, strong SQuAD 2.0 performer, achieves only 67.7% F1 on Molweni‘s questions, a 20+% significant drop as compared against its SQuAD 2.0 performance.
%R 10.18653/v1/2020.coling-main.238
%U https://aclanthology.org/2020.coling-main.238/
%U https://doi.org/10.18653/v1/2020.coling-main.238
%P 2642-2652
Markdown (Informal)
[Molweni: A Challenge Multiparty Dialogues-based Machine Reading Comprehension Dataset with Discourse Structure](https://aclanthology.org/2020.coling-main.238/) (Li et al., COLING 2020)
ACL
- Jiaqi Li, Ming Liu, Min-Yen Kan, Zihao Zheng, Zekun Wang, Wenqiang Lei, Ting Liu, and Bing Qin. 2020. Molweni: A Challenge Multiparty Dialogues-based Machine Reading Comprehension Dataset with Discourse Structure. In Proceedings of the 28th International Conference on Computational Linguistics, pages 2642–2652, Barcelona, Spain (Online). International Committee on Computational Linguistics.