@article{simpson-etal-2020-interactive,
title = "Interactive Text Ranking with {B}ayesian Optimization: A Case Study on Community {QA} and Summarization",
author = "Simpson, Edwin and
Gao, Yang and
Gurevych, Iryna",
editor = "Johnson, Mark and
Roark, Brian and
Nenkova, Ani",
journal = "Transactions of the Association for Computational Linguistics",
volume = "8",
year = "2020",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/2020.tacl-1.49",
doi = "10.1162/tacl_a_00344",
pages = "759--775",
abstract = "For many NLP applications, such as question answering and summarization, the goal is to select the best solution from a large space of candidates to meet a particular user{'}s needs. To address the lack of user or task-specific training data, we propose an interactive text ranking approach that actively selects pairs of candidates, from which the user selects the best. Unlike previous strategies, which attempt to learn a ranking across the whole candidate space, our method uses Bayesian optimization to focus the user{'}s labeling effort on high quality candidates and integrate prior knowledge to cope better with small data scenarios. We apply our method to community question answering (cQA) and extractive multidocument summarization, finding that it significantly outperforms existing interactive approaches. We also show that the ranking function learned by our method is an effective reward function for reinforcement learning, which improves the state of the art for interactive summarization.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="simpson-etal-2020-interactive">
<titleInfo>
<title>Interactive Text Ranking with Bayesian Optimization: A Case Study on Community QA and Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Edwin</namePart>
<namePart type="family">Simpson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iryna</namePart>
<namePart type="family">Gurevych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre authority="bibutilsgt">journal article</genre>
<relatedItem type="host">
<titleInfo>
<title>Transactions of the Association for Computational Linguistics</title>
</titleInfo>
<originInfo>
<issuance>continuing</issuance>
<publisher>MIT Press</publisher>
<place>
<placeTerm type="text">Cambridge, MA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">periodical</genre>
<genre authority="bibutilsgt">academic journal</genre>
</relatedItem>
<abstract>For many NLP applications, such as question answering and summarization, the goal is to select the best solution from a large space of candidates to meet a particular user’s needs. To address the lack of user or task-specific training data, we propose an interactive text ranking approach that actively selects pairs of candidates, from which the user selects the best. Unlike previous strategies, which attempt to learn a ranking across the whole candidate space, our method uses Bayesian optimization to focus the user’s labeling effort on high quality candidates and integrate prior knowledge to cope better with small data scenarios. We apply our method to community question answering (cQA) and extractive multidocument summarization, finding that it significantly outperforms existing interactive approaches. We also show that the ranking function learned by our method is an effective reward function for reinforcement learning, which improves the state of the art for interactive summarization.</abstract>
<identifier type="citekey">simpson-etal-2020-interactive</identifier>
<identifier type="doi">10.1162/tacl_a_00344</identifier>
<location>
<url>https://aclanthology.org/2020.tacl-1.49</url>
</location>
<part>
<date>2020</date>
<detail type="volume"><number>8</number></detail>
<extent unit="page">
<start>759</start>
<end>775</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T Interactive Text Ranking with Bayesian Optimization: A Case Study on Community QA and Summarization
%A Simpson, Edwin
%A Gao, Yang
%A Gurevych, Iryna
%J Transactions of the Association for Computational Linguistics
%D 2020
%V 8
%I MIT Press
%C Cambridge, MA
%F simpson-etal-2020-interactive
%X For many NLP applications, such as question answering and summarization, the goal is to select the best solution from a large space of candidates to meet a particular user’s needs. To address the lack of user or task-specific training data, we propose an interactive text ranking approach that actively selects pairs of candidates, from which the user selects the best. Unlike previous strategies, which attempt to learn a ranking across the whole candidate space, our method uses Bayesian optimization to focus the user’s labeling effort on high quality candidates and integrate prior knowledge to cope better with small data scenarios. We apply our method to community question answering (cQA) and extractive multidocument summarization, finding that it significantly outperforms existing interactive approaches. We also show that the ranking function learned by our method is an effective reward function for reinforcement learning, which improves the state of the art for interactive summarization.
%R 10.1162/tacl_a_00344
%U https://aclanthology.org/2020.tacl-1.49
%U https://doi.org/10.1162/tacl_a_00344
%P 759-775
Markdown (Informal)
[Interactive Text Ranking with Bayesian Optimization: A Case Study on Community QA and Summarization](https://aclanthology.org/2020.tacl-1.49) (Simpson et al., TACL 2020)
ACL