@inproceedings{jacovi-etal-2021-scalable,
title = "Scalable Evaluation and Improvement of Document Set Expansion via Neural Positive-Unlabeled Learning",
author = "Jacovi, Alon and
Niu, Gang and
Goldberg, Yoav and
Sugiyama, Masashi",
editor = "Merlo, Paola and
Tiedemann, Jorg and
Tsarfaty, Reut",
booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.eacl-main.47/",
doi = "10.18653/v1/2021.eacl-main.47",
pages = "581--592",
abstract = "We consider the situation in which a user has collected a small set of documents on a cohesive topic, and they want to retrieve additional documents on this topic from a large collection. Information Retrieval (IR) solutions treat the document set as a query, and look for similar documents in the collection. We propose to extend the IR approach by treating the problem as an instance of positive-unlabeled (PU) learning{---}i.e., learning binary classifiers from only positive (the query documents) and unlabeled (the results of the IR engine) data. Utilizing PU learning for text with big neural networks is a largely unexplored field. We discuss various challenges in applying PU learning to the setting, showing that the standard implementations of state-of-the-art PU solutions fail. We propose solutions for each of the challenges and empirically validate them with ablation tests. We demonstrate the effectiveness of the new method using a series of experiments of retrieving PubMed abstracts adhering to fine-grained topics, showing improvements over the common IR solution and other baselines."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jacovi-etal-2021-scalable">
<titleInfo>
<title>Scalable Evaluation and Improvement of Document Set Expansion via Neural Positive-Unlabeled Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alon</namePart>
<namePart type="family">Jacovi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gang</namePart>
<namePart type="family">Niu</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">Masashi</namePart>
<namePart type="family">Sugiyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paola</namePart>
<namePart type="family">Merlo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reut</namePart>
<namePart type="family">Tsarfaty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We consider the situation in which a user has collected a small set of documents on a cohesive topic, and they want to retrieve additional documents on this topic from a large collection. Information Retrieval (IR) solutions treat the document set as a query, and look for similar documents in the collection. We propose to extend the IR approach by treating the problem as an instance of positive-unlabeled (PU) learning—i.e., learning binary classifiers from only positive (the query documents) and unlabeled (the results of the IR engine) data. Utilizing PU learning for text with big neural networks is a largely unexplored field. We discuss various challenges in applying PU learning to the setting, showing that the standard implementations of state-of-the-art PU solutions fail. We propose solutions for each of the challenges and empirically validate them with ablation tests. We demonstrate the effectiveness of the new method using a series of experiments of retrieving PubMed abstracts adhering to fine-grained topics, showing improvements over the common IR solution and other baselines.</abstract>
<identifier type="citekey">jacovi-etal-2021-scalable</identifier>
<identifier type="doi">10.18653/v1/2021.eacl-main.47</identifier>
<location>
<url>https://aclanthology.org/2021.eacl-main.47/</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>581</start>
<end>592</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Scalable Evaluation and Improvement of Document Set Expansion via Neural Positive-Unlabeled Learning
%A Jacovi, Alon
%A Niu, Gang
%A Goldberg, Yoav
%A Sugiyama, Masashi
%Y Merlo, Paola
%Y Tiedemann, Jorg
%Y Tsarfaty, Reut
%S Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F jacovi-etal-2021-scalable
%X We consider the situation in which a user has collected a small set of documents on a cohesive topic, and they want to retrieve additional documents on this topic from a large collection. Information Retrieval (IR) solutions treat the document set as a query, and look for similar documents in the collection. We propose to extend the IR approach by treating the problem as an instance of positive-unlabeled (PU) learning—i.e., learning binary classifiers from only positive (the query documents) and unlabeled (the results of the IR engine) data. Utilizing PU learning for text with big neural networks is a largely unexplored field. We discuss various challenges in applying PU learning to the setting, showing that the standard implementations of state-of-the-art PU solutions fail. We propose solutions for each of the challenges and empirically validate them with ablation tests. We demonstrate the effectiveness of the new method using a series of experiments of retrieving PubMed abstracts adhering to fine-grained topics, showing improvements over the common IR solution and other baselines.
%R 10.18653/v1/2021.eacl-main.47
%U https://aclanthology.org/2021.eacl-main.47/
%U https://doi.org/10.18653/v1/2021.eacl-main.47
%P 581-592
Markdown (Informal)
[Scalable Evaluation and Improvement of Document Set Expansion via Neural Positive-Unlabeled Learning](https://aclanthology.org/2021.eacl-main.47/) (Jacovi et al., EACL 2021)
ACL