@inproceedings{deschamps-etal-2021-generating,
title = "On Generating Fact-Infused Question Variations",
author = "Deschamps, Arthur and
Gollapalli, Sujatha Das and
Ng, See-Kiong",
booktitle = "Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)",
month = sep,
year = "2021",
address = "Held Online",
publisher = "INCOMA Ltd.",
url = "https://aclanthology.org/2021.ranlp-1.39",
pages = "335--345",
abstract = "To fully model human-like ability to ask questions, automatic question generation (QG) models must be able to produce multiple expressions of the same question with different levels of detail. Unfortunately, existing datasets available for learning QG do not include paraphrases or question variations affecting a model{'}s ability to learn this capability. We present FIRS, a dataset containing human-generated fact-infused rewrites of questions from the widely-used SQuAD dataset to address this limitation. Questions in FIRS were obtained by combining a given question with facts of entities referenced in the question. We study a double encoder-decoder model, Fact-Infused Question Generator (FIQG), for learning to generate fact-infused questions from a given question. Experimental results show that FIQG effectively incorporates information from facts to add more detail to a given question. To the best of our knowledge, ours is the first study to present fact-infusion as a novel form of question paraphrasing.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="deschamps-etal-2021-generating">
<titleInfo>
<title>On Generating Fact-Infused Question Variations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arthur</namePart>
<namePart type="family">Deschamps</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sujatha</namePart>
<namePart type="given">Das</namePart>
<namePart type="family">Gollapalli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">See-Kiong</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-sep</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)</title>
</titleInfo>
<originInfo>
<publisher>INCOMA Ltd.</publisher>
<place>
<placeTerm type="text">Held Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>To fully model human-like ability to ask questions, automatic question generation (QG) models must be able to produce multiple expressions of the same question with different levels of detail. Unfortunately, existing datasets available for learning QG do not include paraphrases or question variations affecting a model’s ability to learn this capability. We present FIRS, a dataset containing human-generated fact-infused rewrites of questions from the widely-used SQuAD dataset to address this limitation. Questions in FIRS were obtained by combining a given question with facts of entities referenced in the question. We study a double encoder-decoder model, Fact-Infused Question Generator (FIQG), for learning to generate fact-infused questions from a given question. Experimental results show that FIQG effectively incorporates information from facts to add more detail to a given question. To the best of our knowledge, ours is the first study to present fact-infusion as a novel form of question paraphrasing.</abstract>
<identifier type="citekey">deschamps-etal-2021-generating</identifier>
<location>
<url>https://aclanthology.org/2021.ranlp-1.39</url>
</location>
<part>
<date>2021-sep</date>
<extent unit="page">
<start>335</start>
<end>345</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On Generating Fact-Infused Question Variations
%A Deschamps, Arthur
%A Gollapalli, Sujatha Das
%A Ng, See-Kiong
%S Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)
%D 2021
%8 sep
%I INCOMA Ltd.
%C Held Online
%F deschamps-etal-2021-generating
%X To fully model human-like ability to ask questions, automatic question generation (QG) models must be able to produce multiple expressions of the same question with different levels of detail. Unfortunately, existing datasets available for learning QG do not include paraphrases or question variations affecting a model’s ability to learn this capability. We present FIRS, a dataset containing human-generated fact-infused rewrites of questions from the widely-used SQuAD dataset to address this limitation. Questions in FIRS were obtained by combining a given question with facts of entities referenced in the question. We study a double encoder-decoder model, Fact-Infused Question Generator (FIQG), for learning to generate fact-infused questions from a given question. Experimental results show that FIQG effectively incorporates information from facts to add more detail to a given question. To the best of our knowledge, ours is the first study to present fact-infusion as a novel form of question paraphrasing.
%U https://aclanthology.org/2021.ranlp-1.39
%P 335-345
Markdown (Informal)
[On Generating Fact-Infused Question Variations](https://aclanthology.org/2021.ranlp-1.39) (Deschamps et al., RANLP 2021)
ACL
- Arthur Deschamps, Sujatha Das Gollapalli, and See-Kiong Ng. 2021. On Generating Fact-Infused Question Variations. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021), pages 335–345, Held Online. INCOMA Ltd..