@inproceedings{pyatkin-etal-2021-asking,
title = "Asking It All: Generating Contextualized Questions for any Semantic Role",
author = "Pyatkin, Valentina and
Roit, Paul and
Michael, Julian and
Goldberg, Yoav and
Tsarfaty, Reut and
Dagan, Ido",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.108",
doi = "10.18653/v1/2021.emnlp-main.108",
pages = "1429--1441",
abstract = "Asking questions about a situation is an inherent step towards understanding it. To this end, we introduce the task of role question generation, which, given a predicate mention and a passage, requires producing a set of questions asking about all possible semantic roles of the predicate. We develop a two-stage model for this task, which first produces a context-independent question prototype for each role and then revises it to be contextually appropriate for the passage. Unlike most existing approaches to question generation, our approach does not require conditioning on existing answers in the text. Instead, we condition on the type of information to inquire about, regardless of whether the answer appears explicitly in the text, could be inferred from it, or should be sought elsewhere. Our evaluation demonstrates that we generate diverse and well-formed questions for a large, broad-coverage ontology of predicates and roles.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pyatkin-etal-2021-asking">
<titleInfo>
<title>Asking It All: Generating Contextualized Questions for any Semantic Role</title>
</titleInfo>
<name type="personal">
<namePart type="given">Valentina</namePart>
<namePart type="family">Pyatkin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Roit</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julian</namePart>
<namePart type="family">Michael</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reut</namePart>
<namePart type="family">Tsarfaty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ido</namePart>
<namePart type="family">Dagan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Asking questions about a situation is an inherent step towards understanding it. To this end, we introduce the task of role question generation, which, given a predicate mention and a passage, requires producing a set of questions asking about all possible semantic roles of the predicate. We develop a two-stage model for this task, which first produces a context-independent question prototype for each role and then revises it to be contextually appropriate for the passage. Unlike most existing approaches to question generation, our approach does not require conditioning on existing answers in the text. Instead, we condition on the type of information to inquire about, regardless of whether the answer appears explicitly in the text, could be inferred from it, or should be sought elsewhere. Our evaluation demonstrates that we generate diverse and well-formed questions for a large, broad-coverage ontology of predicates and roles.</abstract>
<identifier type="citekey">pyatkin-etal-2021-asking</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.108</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.108</url>
</location>
<part>
<date>2021-nov</date>
<extent unit="page">
<start>1429</start>
<end>1441</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Asking It All: Generating Contextualized Questions for any Semantic Role
%A Pyatkin, Valentina
%A Roit, Paul
%A Michael, Julian
%A Goldberg, Yoav
%A Tsarfaty, Reut
%A Dagan, Ido
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 nov
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F pyatkin-etal-2021-asking
%X Asking questions about a situation is an inherent step towards understanding it. To this end, we introduce the task of role question generation, which, given a predicate mention and a passage, requires producing a set of questions asking about all possible semantic roles of the predicate. We develop a two-stage model for this task, which first produces a context-independent question prototype for each role and then revises it to be contextually appropriate for the passage. Unlike most existing approaches to question generation, our approach does not require conditioning on existing answers in the text. Instead, we condition on the type of information to inquire about, regardless of whether the answer appears explicitly in the text, could be inferred from it, or should be sought elsewhere. Our evaluation demonstrates that we generate diverse and well-formed questions for a large, broad-coverage ontology of predicates and roles.
%R 10.18653/v1/2021.emnlp-main.108
%U https://aclanthology.org/2021.emnlp-main.108
%U https://doi.org/10.18653/v1/2021.emnlp-main.108
%P 1429-1441
Markdown (Informal)
[Asking It All: Generating Contextualized Questions for any Semantic Role](https://aclanthology.org/2021.emnlp-main.108) (Pyatkin et al., EMNLP 2021)
ACL
- Valentina Pyatkin, Paul Roit, Julian Michael, Yoav Goldberg, Reut Tsarfaty, and Ido Dagan. 2021. Asking It All: Generating Contextualized Questions for any Semantic Role. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 1429–1441, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.