@inproceedings{cao-etal-2017-modeling,
title = "On Modeling Sense Relatedness in Multi-prototype Word Embedding",
author = "Cao, Yixin and
Shi, Jiaxin and
Li, Juanzi and
Liu, Zhiyuan and
Li, Chengjiang",
editor = "Kondrak, Greg and
Watanabe, Taro",
booktitle = "Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = nov,
year = "2017",
address = "Taipei, Taiwan",
publisher = "Asian Federation of Natural Language Processing",
url = "https://aclanthology.org/I17-1024",
pages = "233--242",
abstract = "To enhance the expression ability of distributional word representation learning model, many researchers tend to induce word senses through clustering, and learn multiple embedding vectors for each word, namely multi-prototype word embedding model. However, most related work ignores the relatedness among word senses which actually plays an important role. In this paper, we propose a novel approach to capture word sense relatedness in multi-prototype word embedding model. Particularly, we differentiate the original sense and extended senses of a word by introducing their global occurrence information and model their relatedness through the local textual context information. Based on the idea of fuzzy clustering, we introduce a random process to integrate these two types of senses and design two non-parametric methods for word sense induction. To make our model more scalable and efficient, we use an online joint learning framework extended from the Skip-gram model. The experimental results demonstrate that our model outperforms both conventional single-prototype embedding models and other multi-prototype embedding models, and achieves more stable performance when trained on smaller data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cao-etal-2017-modeling">
<titleInfo>
<title>On Modeling Sense Relatedness in Multi-prototype Word Embedding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yixin</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaxin</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juanzi</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiyuan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengjiang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Greg</namePart>
<namePart type="family">Kondrak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taro</namePart>
<namePart type="family">Watanabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Asian Federation of Natural Language Processing</publisher>
<place>
<placeTerm type="text">Taipei, Taiwan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>To enhance the expression ability of distributional word representation learning model, many researchers tend to induce word senses through clustering, and learn multiple embedding vectors for each word, namely multi-prototype word embedding model. However, most related work ignores the relatedness among word senses which actually plays an important role. In this paper, we propose a novel approach to capture word sense relatedness in multi-prototype word embedding model. Particularly, we differentiate the original sense and extended senses of a word by introducing their global occurrence information and model their relatedness through the local textual context information. Based on the idea of fuzzy clustering, we introduce a random process to integrate these two types of senses and design two non-parametric methods for word sense induction. To make our model more scalable and efficient, we use an online joint learning framework extended from the Skip-gram model. The experimental results demonstrate that our model outperforms both conventional single-prototype embedding models and other multi-prototype embedding models, and achieves more stable performance when trained on smaller data.</abstract>
<identifier type="citekey">cao-etal-2017-modeling</identifier>
<location>
<url>https://aclanthology.org/I17-1024</url>
</location>
<part>
<date>2017-11</date>
<extent unit="page">
<start>233</start>
<end>242</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On Modeling Sense Relatedness in Multi-prototype Word Embedding
%A Cao, Yixin
%A Shi, Jiaxin
%A Li, Juanzi
%A Liu, Zhiyuan
%A Li, Chengjiang
%Y Kondrak, Greg
%Y Watanabe, Taro
%S Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2017
%8 November
%I Asian Federation of Natural Language Processing
%C Taipei, Taiwan
%F cao-etal-2017-modeling
%X To enhance the expression ability of distributional word representation learning model, many researchers tend to induce word senses through clustering, and learn multiple embedding vectors for each word, namely multi-prototype word embedding model. However, most related work ignores the relatedness among word senses which actually plays an important role. In this paper, we propose a novel approach to capture word sense relatedness in multi-prototype word embedding model. Particularly, we differentiate the original sense and extended senses of a word by introducing their global occurrence information and model their relatedness through the local textual context information. Based on the idea of fuzzy clustering, we introduce a random process to integrate these two types of senses and design two non-parametric methods for word sense induction. To make our model more scalable and efficient, we use an online joint learning framework extended from the Skip-gram model. The experimental results demonstrate that our model outperforms both conventional single-prototype embedding models and other multi-prototype embedding models, and achieves more stable performance when trained on smaller data.
%U https://aclanthology.org/I17-1024
%P 233-242
Markdown (Informal)
[On Modeling Sense Relatedness in Multi-prototype Word Embedding](https://aclanthology.org/I17-1024) (Cao et al., IJCNLP 2017)
ACL
- Yixin Cao, Jiaxin Shi, Juanzi Li, Zhiyuan Liu, and Chengjiang Li. 2017. On Modeling Sense Relatedness in Multi-prototype Word Embedding. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 233–242, Taipei, Taiwan. Asian Federation of Natural Language Processing.