@inproceedings{patra-etal-2020-scopeit,
title = "{S}cope{I}t: Scoping Task Relevant Sentences in Documents",
author = "Patra, Barun and
Suryanarayanan, Vishwas and
Fufa, Chala and
Bhattacharya, Pamela and
Lee, Charles",
editor = "Clifton, Ann and
Napoles, Courtney",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics: Industry Track",
month = dec,
year = "2020",
address = "Online",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-industry.20/",
doi = "10.18653/v1/2020.coling-industry.20",
pages = "214--227",
abstract = "A prominent problem faced by conversational agents working with large documents (Eg: email-based assistants) is the frequent presence of information in the document that is irrelevant to the assistant. This in turn makes it harder for the agent to accurately detect intents, extract entities relevant to those intents and perform the desired action. To address this issue we present a neural model for scoping relevant information for the agent from a large document. We show that when used as the first step in a popularly used email-based assistant for helping users schedule meetings, our proposed model helps improve the performance of the intent detection and entity extraction tasks required by the agent for correctly scheduling meetings: across a suite of 6 downstream tasks, by using our proposed method, we observe an average gain of 35{\%} in precision without any drop in recall. Additionally, we demonstrate that the same approach can be used for component level analysis in large documents, such as signature block identification."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="patra-etal-2020-scopeit">
<titleInfo>
<title>ScopeIt: Scoping Task Relevant Sentences in Documents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Barun</namePart>
<namePart type="family">Patra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vishwas</namePart>
<namePart type="family">Suryanarayanan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chala</namePart>
<namePart type="family">Fufa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pamela</namePart>
<namePart type="family">Bhattacharya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Charles</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ann</namePart>
<namePart type="family">Clifton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Courtney</namePart>
<namePart type="family">Napoles</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>A prominent problem faced by conversational agents working with large documents (Eg: email-based assistants) is the frequent presence of information in the document that is irrelevant to the assistant. This in turn makes it harder for the agent to accurately detect intents, extract entities relevant to those intents and perform the desired action. To address this issue we present a neural model for scoping relevant information for the agent from a large document. We show that when used as the first step in a popularly used email-based assistant for helping users schedule meetings, our proposed model helps improve the performance of the intent detection and entity extraction tasks required by the agent for correctly scheduling meetings: across a suite of 6 downstream tasks, by using our proposed method, we observe an average gain of 35% in precision without any drop in recall. Additionally, we demonstrate that the same approach can be used for component level analysis in large documents, such as signature block identification.</abstract>
<identifier type="citekey">patra-etal-2020-scopeit</identifier>
<identifier type="doi">10.18653/v1/2020.coling-industry.20</identifier>
<location>
<url>https://aclanthology.org/2020.coling-industry.20/</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>214</start>
<end>227</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ScopeIt: Scoping Task Relevant Sentences in Documents
%A Patra, Barun
%A Suryanarayanan, Vishwas
%A Fufa, Chala
%A Bhattacharya, Pamela
%A Lee, Charles
%Y Clifton, Ann
%Y Napoles, Courtney
%S Proceedings of the 28th International Conference on Computational Linguistics: Industry Track
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Online
%F patra-etal-2020-scopeit
%X A prominent problem faced by conversational agents working with large documents (Eg: email-based assistants) is the frequent presence of information in the document that is irrelevant to the assistant. This in turn makes it harder for the agent to accurately detect intents, extract entities relevant to those intents and perform the desired action. To address this issue we present a neural model for scoping relevant information for the agent from a large document. We show that when used as the first step in a popularly used email-based assistant for helping users schedule meetings, our proposed model helps improve the performance of the intent detection and entity extraction tasks required by the agent for correctly scheduling meetings: across a suite of 6 downstream tasks, by using our proposed method, we observe an average gain of 35% in precision without any drop in recall. Additionally, we demonstrate that the same approach can be used for component level analysis in large documents, such as signature block identification.
%R 10.18653/v1/2020.coling-industry.20
%U https://aclanthology.org/2020.coling-industry.20/
%U https://doi.org/10.18653/v1/2020.coling-industry.20
%P 214-227
Markdown (Informal)
[ScopeIt: Scoping Task Relevant Sentences in Documents](https://aclanthology.org/2020.coling-industry.20/) (Patra et al., COLING 2020)
ACL
- Barun Patra, Vishwas Suryanarayanan, Chala Fufa, Pamela Bhattacharya, and Charles Lee. 2020. ScopeIt: Scoping Task Relevant Sentences in Documents. In Proceedings of the 28th International Conference on Computational Linguistics: Industry Track, pages 214–227, Online. International Committee on Computational Linguistics.