@inproceedings{faruqui-das-2018-identifying,
title = "Identifying Well-formed Natural Language Questions",
author = "Faruqui, Manaal and
Das, Dipanjan",
editor = "Riloff, Ellen and
Chiang, David and
Hockenmaier, Julia and
Tsujii, Jun{'}ichi",
booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing",
month = oct # "-" # nov,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D18-1091",
doi = "10.18653/v1/D18-1091",
pages = "798--803",
abstract = "Understanding search queries is a hard problem as it involves dealing with {``}word salad{''} text ubiquitously issued by users. However, if a query resembles a well-formed question, a natural language processing pipeline is able to perform more accurate interpretation, thus reducing downstream compounding errors. Hence, identifying whether or not a query is well formed can enhance query understanding. Here, we introduce a new task of identifying a well-formed natural language question. We construct and release a dataset of 25,100 publicly available questions classified into well-formed and non-wellformed categories and report an accuracy of 70.7{\%} on the test set. We also show that our classifier can be used to improve the performance of neural sequence-to-sequence models for generating questions for reading comprehension.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="faruqui-das-2018-identifying">
<titleInfo>
<title>Identifying Well-formed Natural Language Questions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Manaal</namePart>
<namePart type="family">Faruqui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dipanjan</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-oct-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ellen</namePart>
<namePart type="family">Riloff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Chiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="family">Hockenmaier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun’ichi</namePart>
<namePart type="family">Tsujii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Brussels, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Understanding search queries is a hard problem as it involves dealing with “word salad” text ubiquitously issued by users. However, if a query resembles a well-formed question, a natural language processing pipeline is able to perform more accurate interpretation, thus reducing downstream compounding errors. Hence, identifying whether or not a query is well formed can enhance query understanding. Here, we introduce a new task of identifying a well-formed natural language question. We construct and release a dataset of 25,100 publicly available questions classified into well-formed and non-wellformed categories and report an accuracy of 70.7% on the test set. We also show that our classifier can be used to improve the performance of neural sequence-to-sequence models for generating questions for reading comprehension.</abstract>
<identifier type="citekey">faruqui-das-2018-identifying</identifier>
<identifier type="doi">10.18653/v1/D18-1091</identifier>
<location>
<url>https://aclanthology.org/D18-1091</url>
</location>
<part>
<date>2018-oct-nov</date>
<extent unit="page">
<start>798</start>
<end>803</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Identifying Well-formed Natural Language Questions
%A Faruqui, Manaal
%A Das, Dipanjan
%Y Riloff, Ellen
%Y Chiang, David
%Y Hockenmaier, Julia
%Y Tsujii, Jun’ichi
%S Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
%D 2018
%8 oct nov
%I Association for Computational Linguistics
%C Brussels, Belgium
%F faruqui-das-2018-identifying
%X Understanding search queries is a hard problem as it involves dealing with “word salad” text ubiquitously issued by users. However, if a query resembles a well-formed question, a natural language processing pipeline is able to perform more accurate interpretation, thus reducing downstream compounding errors. Hence, identifying whether or not a query is well formed can enhance query understanding. Here, we introduce a new task of identifying a well-formed natural language question. We construct and release a dataset of 25,100 publicly available questions classified into well-formed and non-wellformed categories and report an accuracy of 70.7% on the test set. We also show that our classifier can be used to improve the performance of neural sequence-to-sequence models for generating questions for reading comprehension.
%R 10.18653/v1/D18-1091
%U https://aclanthology.org/D18-1091
%U https://doi.org/10.18653/v1/D18-1091
%P 798-803
Markdown (Informal)
[Identifying Well-formed Natural Language Questions](https://aclanthology.org/D18-1091) (Faruqui & Das, EMNLP 2018)
ACL
- Manaal Faruqui and Dipanjan Das. 2018. Identifying Well-formed Natural Language Questions. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 798–803, Brussels, Belgium. Association for Computational Linguistics.