@inproceedings{deriu-etal-2020-methodology,
title = "A Methodology for Creating Question Answering Corpora Using Inverse Data Annotation",
author = {Deriu, Jan and
Mlynchyk, Katsiaryna and
Schl{\"a}pfer, Philippe and
Rodrigo, Alvaro and
von Gr{\"u}nigen, Dirk and
Kaiser, Nicolas and
Stockinger, Kurt and
Agirre, Eneko and
Cieliebak, Mark},
editor = "Jurafsky, Dan and
Chai, Joyce and
Schluter, Natalie and
Tetreault, Joel",
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.acl-main.84",
doi = "10.18653/v1/2020.acl-main.84",
pages = "897--911",
abstract = "In this paper, we introduce a novel methodology to efficiently construct a corpus for question answering over structured data. For this, we introduce an intermediate representation that is based on the logical query plan in a database, called Operation Trees (OT). This representation allows us to invert the annotation process without loosing flexibility in the types of queries that we generate. Furthermore, it allows for fine-grained alignment of the tokens to the operations. Thus, we randomly generate OTs from a context free grammar and annotators just have to write the appropriate question and assign the tokens. We compare our corpus OTTA (Operation Trees and Token Assignment), a large semantic parsing corpus for evaluating natural language interfaces to databases, to Spider and LC-QuaD 2.0 and show that our methodology more than triples the annotation speed while maintaining the complexity of the queries. Finally, we train a state-of-the-art semantic parsing model on our data and show that our dataset is a challenging dataset and that the token alignment can be leveraged to significantly increase the performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="deriu-etal-2020-methodology">
<titleInfo>
<title>A Methodology for Creating Question Answering Corpora Using Inverse Data Annotation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Deriu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katsiaryna</namePart>
<namePart type="family">Mlynchyk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Schläpfer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alvaro</namePart>
<namePart type="family">Rodrigo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dirk</namePart>
<namePart type="family">von Grünigen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicolas</namePart>
<namePart type="family">Kaiser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kurt</namePart>
<namePart type="family">Stockinger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eneko</namePart>
<namePart type="family">Agirre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Cieliebak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Jurafsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Chai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Schluter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="family">Tetreault</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>In this paper, we introduce a novel methodology to efficiently construct a corpus for question answering over structured data. For this, we introduce an intermediate representation that is based on the logical query plan in a database, called Operation Trees (OT). This representation allows us to invert the annotation process without loosing flexibility in the types of queries that we generate. Furthermore, it allows for fine-grained alignment of the tokens to the operations. Thus, we randomly generate OTs from a context free grammar and annotators just have to write the appropriate question and assign the tokens. We compare our corpus OTTA (Operation Trees and Token Assignment), a large semantic parsing corpus for evaluating natural language interfaces to databases, to Spider and LC-QuaD 2.0 and show that our methodology more than triples the annotation speed while maintaining the complexity of the queries. Finally, we train a state-of-the-art semantic parsing model on our data and show that our dataset is a challenging dataset and that the token alignment can be leveraged to significantly increase the performance.</abstract>
<identifier type="citekey">deriu-etal-2020-methodology</identifier>
<identifier type="doi">10.18653/v1/2020.acl-main.84</identifier>
<location>
<url>https://aclanthology.org/2020.acl-main.84</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>897</start>
<end>911</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Methodology for Creating Question Answering Corpora Using Inverse Data Annotation
%A Deriu, Jan
%A Mlynchyk, Katsiaryna
%A Schläpfer, Philippe
%A Rodrigo, Alvaro
%A von Grünigen, Dirk
%A Kaiser, Nicolas
%A Stockinger, Kurt
%A Agirre, Eneko
%A Cieliebak, Mark
%Y Jurafsky, Dan
%Y Chai, Joyce
%Y Schluter, Natalie
%Y Tetreault, Joel
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F deriu-etal-2020-methodology
%X In this paper, we introduce a novel methodology to efficiently construct a corpus for question answering over structured data. For this, we introduce an intermediate representation that is based on the logical query plan in a database, called Operation Trees (OT). This representation allows us to invert the annotation process without loosing flexibility in the types of queries that we generate. Furthermore, it allows for fine-grained alignment of the tokens to the operations. Thus, we randomly generate OTs from a context free grammar and annotators just have to write the appropriate question and assign the tokens. We compare our corpus OTTA (Operation Trees and Token Assignment), a large semantic parsing corpus for evaluating natural language interfaces to databases, to Spider and LC-QuaD 2.0 and show that our methodology more than triples the annotation speed while maintaining the complexity of the queries. Finally, we train a state-of-the-art semantic parsing model on our data and show that our dataset is a challenging dataset and that the token alignment can be leveraged to significantly increase the performance.
%R 10.18653/v1/2020.acl-main.84
%U https://aclanthology.org/2020.acl-main.84
%U https://doi.org/10.18653/v1/2020.acl-main.84
%P 897-911
Markdown (Informal)
[A Methodology for Creating Question Answering Corpora Using Inverse Data Annotation](https://aclanthology.org/2020.acl-main.84) (Deriu et al., ACL 2020)
ACL
- Jan Deriu, Katsiaryna Mlynchyk, Philippe Schläpfer, Alvaro Rodrigo, Dirk von Grünigen, Nicolas Kaiser, Kurt Stockinger, Eneko Agirre, and Mark Cieliebak. 2020. A Methodology for Creating Question Answering Corpora Using Inverse Data Annotation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 897–911, Online. Association for Computational Linguistics.