@inproceedings{zhuang-etal-2017-identifying,
title = "Identifying Semantically Deviating Outlier Documents",
author = "Zhuang, Honglei and
Wang, Chi and
Tao, Fangbo and
Kaplan, Lance and
Han, Jiawei",
editor = "Palmer, Martha and
Hwa, Rebecca and
Riedel, Sebastian",
booktitle = "Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing",
month = sep,
year = "2017",
address = "Copenhagen, Denmark",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D17-1291",
doi = "10.18653/v1/D17-1291",
pages = "2748--2757",
abstract = "A document outlier is a document that substantially deviates in semantics from the majority ones in a corpus. Automatic identification of document outliers can be valuable in many applications, such as screening health records for medical mistakes. In this paper, we study the problem of mining semantically deviating document outliers in a given corpus. We develop a generative model to identify frequent and characteristic semantic regions in the word embedding space to represent the given corpus, and a robust outlierness measure which is resistant to noisy content in documents. Experiments conducted on two real-world textual data sets show that our method can achieve an up to 135{\%} improvement over baselines in terms of recall at top-1{\%} of the outlier ranking.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhuang-etal-2017-identifying">
<titleInfo>
<title>Identifying Semantically Deviating Outlier Documents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Honglei</namePart>
<namePart type="family">Zhuang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fangbo</namePart>
<namePart type="family">Tao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lance</namePart>
<namePart type="family">Kaplan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiawei</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Martha</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rebecca</namePart>
<namePart type="family">Hwa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Riedel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Copenhagen, Denmark</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>A document outlier is a document that substantially deviates in semantics from the majority ones in a corpus. Automatic identification of document outliers can be valuable in many applications, such as screening health records for medical mistakes. In this paper, we study the problem of mining semantically deviating document outliers in a given corpus. We develop a generative model to identify frequent and characteristic semantic regions in the word embedding space to represent the given corpus, and a robust outlierness measure which is resistant to noisy content in documents. Experiments conducted on two real-world textual data sets show that our method can achieve an up to 135% improvement over baselines in terms of recall at top-1% of the outlier ranking.</abstract>
<identifier type="citekey">zhuang-etal-2017-identifying</identifier>
<identifier type="doi">10.18653/v1/D17-1291</identifier>
<location>
<url>https://aclanthology.org/D17-1291</url>
</location>
<part>
<date>2017-09</date>
<extent unit="page">
<start>2748</start>
<end>2757</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Identifying Semantically Deviating Outlier Documents
%A Zhuang, Honglei
%A Wang, Chi
%A Tao, Fangbo
%A Kaplan, Lance
%A Han, Jiawei
%Y Palmer, Martha
%Y Hwa, Rebecca
%Y Riedel, Sebastian
%S Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
%D 2017
%8 September
%I Association for Computational Linguistics
%C Copenhagen, Denmark
%F zhuang-etal-2017-identifying
%X A document outlier is a document that substantially deviates in semantics from the majority ones in a corpus. Automatic identification of document outliers can be valuable in many applications, such as screening health records for medical mistakes. In this paper, we study the problem of mining semantically deviating document outliers in a given corpus. We develop a generative model to identify frequent and characteristic semantic regions in the word embedding space to represent the given corpus, and a robust outlierness measure which is resistant to noisy content in documents. Experiments conducted on two real-world textual data sets show that our method can achieve an up to 135% improvement over baselines in terms of recall at top-1% of the outlier ranking.
%R 10.18653/v1/D17-1291
%U https://aclanthology.org/D17-1291
%U https://doi.org/10.18653/v1/D17-1291
%P 2748-2757
Markdown (Informal)
[Identifying Semantically Deviating Outlier Documents](https://aclanthology.org/D17-1291) (Zhuang et al., EMNLP 2017)
ACL
- Honglei Zhuang, Chi Wang, Fangbo Tao, Lance Kaplan, and Jiawei Han. 2017. Identifying Semantically Deviating Outlier Documents. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2748–2757, Copenhagen, Denmark. Association for Computational Linguistics.