@inproceedings{song-lee-2017-learning,
title = "Learning User Embeddings from Emails",
author = "Song, Yan and
Lee, Chia-Jung",
editor = "Lapata, Mirella and
Blunsom, Phil and
Koller, Alexander",
booktitle = "Proceedings of the 15th Conference of the {E}uropean Chapter of the Association for Computational Linguistics: Volume 2, Short Papers",
month = apr,
year = "2017",
address = "Valencia, Spain",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/E17-2116",
pages = "733--738",
abstract = "Many important email-related tasks, such as email classification or search, highly rely on building quality document representations (e.g., bag-of-words or key phrases) to assist matching and understanding. Despite prior success on representing textual messages, creating quality user representations from emails was overlooked. In this paper, we propose to represent users using embeddings that are trained to reflect the email communication network. Our experiments on Enron dataset suggest that the resulting embeddings capture the semantic distance between users. To assess the quality of embeddings in a real-world application, we carry out auto-foldering task where the lexical representation of an email is enriched with user embedding features. Our results show that folder prediction accuracy is improved when embedding features are present across multiple settings.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="song-lee-2017-learning">
<titleInfo>
<title>Learning User Embeddings from Emails</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chia-Jung</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mirella</namePart>
<namePart type="family">Lapata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phil</namePart>
<namePart type="family">Blunsom</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Koller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Valencia, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Many important email-related tasks, such as email classification or search, highly rely on building quality document representations (e.g., bag-of-words or key phrases) to assist matching and understanding. Despite prior success on representing textual messages, creating quality user representations from emails was overlooked. In this paper, we propose to represent users using embeddings that are trained to reflect the email communication network. Our experiments on Enron dataset suggest that the resulting embeddings capture the semantic distance between users. To assess the quality of embeddings in a real-world application, we carry out auto-foldering task where the lexical representation of an email is enriched with user embedding features. Our results show that folder prediction accuracy is improved when embedding features are present across multiple settings.</abstract>
<identifier type="citekey">song-lee-2017-learning</identifier>
<location>
<url>https://aclanthology.org/E17-2116</url>
</location>
<part>
<date>2017-04</date>
<extent unit="page">
<start>733</start>
<end>738</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning User Embeddings from Emails
%A Song, Yan
%A Lee, Chia-Jung
%Y Lapata, Mirella
%Y Blunsom, Phil
%Y Koller, Alexander
%S Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers
%D 2017
%8 April
%I Association for Computational Linguistics
%C Valencia, Spain
%F song-lee-2017-learning
%X Many important email-related tasks, such as email classification or search, highly rely on building quality document representations (e.g., bag-of-words or key phrases) to assist matching and understanding. Despite prior success on representing textual messages, creating quality user representations from emails was overlooked. In this paper, we propose to represent users using embeddings that are trained to reflect the email communication network. Our experiments on Enron dataset suggest that the resulting embeddings capture the semantic distance between users. To assess the quality of embeddings in a real-world application, we carry out auto-foldering task where the lexical representation of an email is enriched with user embedding features. Our results show that folder prediction accuracy is improved when embedding features are present across multiple settings.
%U https://aclanthology.org/E17-2116
%P 733-738
Markdown (Informal)
[Learning User Embeddings from Emails](https://aclanthology.org/E17-2116) (Song & Lee, EACL 2017)
ACL
- Yan Song and Chia-Jung Lee. 2017. Learning User Embeddings from Emails. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pages 733–738, Valencia, Spain. Association for Computational Linguistics.