@inproceedings{eden-etal-2023-welcome,
title = "Welcome to the Real World: Efficient, Incremental and Scalable Key Point Analysis",
author = "Eden, Lilach and
Kantor, Yoav and
Orbach, Matan and
Katz, Yoav and
Slonim, Noam and
Bar-Haim, Roy",
editor = "Wang, Mingxuan and
Zitouni, Imed",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-industry.46",
doi = "10.18653/v1/2023.emnlp-industry.46",
pages = "483--491",
abstract = "Key Point Analysis (KPA) is an emerging summarization framework, which extracts the main points from a collection of opinions, and quantifies their prevalence. It has been successfully applied to diverse types of data, including arguments, user reviews and survey responses. Despite the growing academic interest in KPA, little attention has been given to the practical challenges of implementing a KPA system in production. This work presents a deployed KPA system, which regularly serves multiple teams in our organization. We discuss the main challenges we faced while building a real-world KPA system, as well as the architecture and algorithmic improvements we developed to address these challenges. Specifically, we focus on efficient matching of sentences to key points, incremental processing, scalability and resiliency. The value of our contributions is demonstrated in an extensive set of experiments, over five existing and novel datasets. Finally, we describe several use cases of the deployed system, which illustrate its practical value.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="eden-etal-2023-welcome">
<titleInfo>
<title>Welcome to the Real World: Efficient, Incremental and Scalable Key Point Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lilach</namePart>
<namePart type="family">Eden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Kantor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matan</namePart>
<namePart type="family">Orbach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Katz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Noam</namePart>
<namePart type="family">Slonim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roy</namePart>
<namePart type="family">Bar-Haim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mingxuan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Key Point Analysis (KPA) is an emerging summarization framework, which extracts the main points from a collection of opinions, and quantifies their prevalence. It has been successfully applied to diverse types of data, including arguments, user reviews and survey responses. Despite the growing academic interest in KPA, little attention has been given to the practical challenges of implementing a KPA system in production. This work presents a deployed KPA system, which regularly serves multiple teams in our organization. We discuss the main challenges we faced while building a real-world KPA system, as well as the architecture and algorithmic improvements we developed to address these challenges. Specifically, we focus on efficient matching of sentences to key points, incremental processing, scalability and resiliency. The value of our contributions is demonstrated in an extensive set of experiments, over five existing and novel datasets. Finally, we describe several use cases of the deployed system, which illustrate its practical value.</abstract>
<identifier type="citekey">eden-etal-2023-welcome</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-industry.46</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-industry.46</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>483</start>
<end>491</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Welcome to the Real World: Efficient, Incremental and Scalable Key Point Analysis
%A Eden, Lilach
%A Kantor, Yoav
%A Orbach, Matan
%A Katz, Yoav
%A Slonim, Noam
%A Bar-Haim, Roy
%Y Wang, Mingxuan
%Y Zitouni, Imed
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F eden-etal-2023-welcome
%X Key Point Analysis (KPA) is an emerging summarization framework, which extracts the main points from a collection of opinions, and quantifies their prevalence. It has been successfully applied to diverse types of data, including arguments, user reviews and survey responses. Despite the growing academic interest in KPA, little attention has been given to the practical challenges of implementing a KPA system in production. This work presents a deployed KPA system, which regularly serves multiple teams in our organization. We discuss the main challenges we faced while building a real-world KPA system, as well as the architecture and algorithmic improvements we developed to address these challenges. Specifically, we focus on efficient matching of sentences to key points, incremental processing, scalability and resiliency. The value of our contributions is demonstrated in an extensive set of experiments, over five existing and novel datasets. Finally, we describe several use cases of the deployed system, which illustrate its practical value.
%R 10.18653/v1/2023.emnlp-industry.46
%U https://aclanthology.org/2023.emnlp-industry.46
%U https://doi.org/10.18653/v1/2023.emnlp-industry.46
%P 483-491
Markdown (Informal)
[Welcome to the Real World: Efficient, Incremental and Scalable Key Point Analysis](https://aclanthology.org/2023.emnlp-industry.46) (Eden et al., EMNLP 2023)
ACL