@inproceedings{song-etal-2017-learning,
title = "Learning Word Representations with Regularization from Prior Knowledge",
author = "Song, Yan and
Lee, Chia-Jung and
Xia, Fei",
editor = "Levy, Roger and
Specia, Lucia",
booktitle = "Proceedings of the 21st Conference on Computational Natural Language Learning ({C}o{NLL} 2017)",
month = aug,
year = "2017",
address = "Vancouver, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/K17-1016",
doi = "10.18653/v1/K17-1016",
pages = "143--152",
abstract = "Conventional word embeddings are trained with specific criteria (e.g., based on language modeling or co-occurrence) inside a single information source, disregarding the opportunity for further calibration using external knowledge. This paper presents a unified framework that leverages pre-learned or external priors, in the form of a regularizer, for enhancing conventional language model-based embedding learning. We consider two types of regularizers. The first type is derived from topic distribution by running LDA on unlabeled data. The second type is based on dictionaries that are created with human annotation efforts. To effectively learn with the regularizers, we propose a novel data structure, trajectory softmax, in this paper. The resulting embeddings are evaluated by word similarity and sentiment classification. Experimental results show that our learning framework with regularization from prior knowledge improves embedding quality across multiple datasets, compared to a diverse collection of baseline methods.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="song-etal-2017-learning">
<titleInfo>
<title>Learning Word Representations with Regularization from Prior Knowledge</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>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Roger</namePart>
<namePart type="family">Levy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vancouver, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Conventional word embeddings are trained with specific criteria (e.g., based on language modeling or co-occurrence) inside a single information source, disregarding the opportunity for further calibration using external knowledge. This paper presents a unified framework that leverages pre-learned or external priors, in the form of a regularizer, for enhancing conventional language model-based embedding learning. We consider two types of regularizers. The first type is derived from topic distribution by running LDA on unlabeled data. The second type is based on dictionaries that are created with human annotation efforts. To effectively learn with the regularizers, we propose a novel data structure, trajectory softmax, in this paper. The resulting embeddings are evaluated by word similarity and sentiment classification. Experimental results show that our learning framework with regularization from prior knowledge improves embedding quality across multiple datasets, compared to a diverse collection of baseline methods.</abstract>
<identifier type="citekey">song-etal-2017-learning</identifier>
<identifier type="doi">10.18653/v1/K17-1016</identifier>
<location>
<url>https://aclanthology.org/K17-1016</url>
</location>
<part>
<date>2017-08</date>
<extent unit="page">
<start>143</start>
<end>152</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning Word Representations with Regularization from Prior Knowledge
%A Song, Yan
%A Lee, Chia-Jung
%A Xia, Fei
%Y Levy, Roger
%Y Specia, Lucia
%S Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017)
%D 2017
%8 August
%I Association for Computational Linguistics
%C Vancouver, Canada
%F song-etal-2017-learning
%X Conventional word embeddings are trained with specific criteria (e.g., based on language modeling or co-occurrence) inside a single information source, disregarding the opportunity for further calibration using external knowledge. This paper presents a unified framework that leverages pre-learned or external priors, in the form of a regularizer, for enhancing conventional language model-based embedding learning. We consider two types of regularizers. The first type is derived from topic distribution by running LDA on unlabeled data. The second type is based on dictionaries that are created with human annotation efforts. To effectively learn with the regularizers, we propose a novel data structure, trajectory softmax, in this paper. The resulting embeddings are evaluated by word similarity and sentiment classification. Experimental results show that our learning framework with regularization from prior knowledge improves embedding quality across multiple datasets, compared to a diverse collection of baseline methods.
%R 10.18653/v1/K17-1016
%U https://aclanthology.org/K17-1016
%U https://doi.org/10.18653/v1/K17-1016
%P 143-152
Markdown (Informal)
[Learning Word Representations with Regularization from Prior Knowledge](https://aclanthology.org/K17-1016) (Song et al., CoNLL 2017)
ACL