<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pal-etal-2019-answering">
    <titleInfo>
        <title>Answering Naturally: Factoid to Full length Answer Generation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Vaishali</namePart>
        <namePart type="family">Pal</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Manish</namePart>
        <namePart type="family">Shrivastava</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Irshad</namePart>
        <namePart type="family">Bhat</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-nov</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2nd Workshop on New Frontiers in Summarization</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Hong Kong, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>In recent years, the task of Question Answering over passages, also pitched as a reading comprehension, has evolved into a very active research area. A reading comprehension system extracts a span of text, comprising of named entities, dates, small phrases, etc., which serve as the answer to a given question. However, these spans of text would result in an unnatural reading experience in a conversational system. Usually, dialogue systems solve this issue by using template-based language generation. These systems, though adequate for a domain specific task, are too restrictive and predefined for a domain independent system. In order to present the user with a more conversational experience, we propose a pointer generator based full-length answer generator which can be used with most QA systems. Our system generates a full length answer given a question and the extracted factoid/span answer without relying on the passage from where the answer was extracted. We also present a dataset of 315000 question, factoid answer and full length answer triples. We have evaluated our system using ROUGE-1,2,L and BLEU and achieved 74.05 BLEU score and 86.25 Rogue-L score.</abstract>
    <identifier type="citekey">pal-etal-2019-answering</identifier>
    <identifier type="doi">10.18653/v1/D19-5401</identifier>
    <location>
        <url>https://aclanthology.org/D19-5401</url>
    </location>
    <part>
        <date>2019-nov</date>
        <extent unit="page">
            <start>1</start>
            <end>9</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Answering Naturally: Factoid to Full length Answer Generation
%A Pal, Vaishali
%A Shrivastava, Manish
%A Bhat, Irshad
%S Proceedings of the 2nd Workshop on New Frontiers in Summarization
%D 2019
%8 nov
%I Association for Computational Linguistics
%C Hong Kong, China
%F pal-etal-2019-answering
%X In recent years, the task of Question Answering over passages, also pitched as a reading comprehension, has evolved into a very active research area. A reading comprehension system extracts a span of text, comprising of named entities, dates, small phrases, etc., which serve as the answer to a given question. However, these spans of text would result in an unnatural reading experience in a conversational system. Usually, dialogue systems solve this issue by using template-based language generation. These systems, though adequate for a domain specific task, are too restrictive and predefined for a domain independent system. In order to present the user with a more conversational experience, we propose a pointer generator based full-length answer generator which can be used with most QA systems. Our system generates a full length answer given a question and the extracted factoid/span answer without relying on the passage from where the answer was extracted. We also present a dataset of 315000 question, factoid answer and full length answer triples. We have evaluated our system using ROUGE-1,2,L and BLEU and achieved 74.05 BLEU score and 86.25 Rogue-L score.
%R 10.18653/v1/D19-5401
%U https://aclanthology.org/D19-5401
%U https://doi.org/10.18653/v1/D19-5401
%P 1-9

Markdown (Informal)

[Answering Naturally: Factoid to Full length Answer Generation](https://aclanthology.org/D19-5401) (Pal et al., EMNLP 2019)

• Answering Naturally: Factoid to Full length Answer Generation (Pal et al., EMNLP 2019)

ACL

• Vaishali Pal, Manish Shrivastava, and Irshad Bhat. 2019. Answering Naturally: Factoid to Full length Answer Generation. In Proceedings of the 2nd Workshop on New Frontiers in Summarization, pages 1–9, Hong Kong, China. Association for Computational Linguistics.