@inproceedings{masumura-etal-2017-hyperspherical,
title = "Hyperspherical Query Likelihood Models with Word Embeddings",
author = "Masumura, Ryo and
Asami, Taichi and
Masataki, Hirokazu and
Sadamitsu, Kugatsu and
Nishida, Kyosuke and
Higashinaka, Ryuichiro",
editor = "Kondrak, Greg and
Watanabe, Taro",
booktitle = "Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)",
month = nov,
year = "2017",
address = "Taipei, Taiwan",
publisher = "Asian Federation of Natural Language Processing",
url = "https://aclanthology.org/I17-2036/",
pages = "210--216",
abstract = "This paper presents an initial study on hyperspherical query likelihood models (QLMs) for information retrieval (IR). Our motivation is to naturally utilize pre-trained word embeddings for probabilistic IR. To this end, key idea is to directly leverage the word embeddings as random variables for directional probabilistic models based on von Mises-Fisher distributions which are familiar to cosine distances. The proposed method enables us to theoretically take semantic similarities between document and target queries into consideration without introducing heuristic expansion techniques. In addition, this paper reveals relationships between hyperspherical QLMs and conventional QLMs. Experiments show document retrieval evaluation results in which a hyperspherical QLM is compared to conventional QLMs and document distance metrics using word or document embeddings."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="masumura-etal-2017-hyperspherical">
<titleInfo>
<title>Hyperspherical Query Likelihood Models with Word Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ryo</namePart>
<namePart type="family">Masumura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taichi</namePart>
<namePart type="family">Asami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hirokazu</namePart>
<namePart type="family">Masataki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kugatsu</namePart>
<namePart type="family">Sadamitsu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyosuke</namePart>
<namePart type="family">Nishida</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryuichiro</namePart>
<namePart type="family">Higashinaka</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 2: Short 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>This paper presents an initial study on hyperspherical query likelihood models (QLMs) for information retrieval (IR). Our motivation is to naturally utilize pre-trained word embeddings for probabilistic IR. To this end, key idea is to directly leverage the word embeddings as random variables for directional probabilistic models based on von Mises-Fisher distributions which are familiar to cosine distances. The proposed method enables us to theoretically take semantic similarities between document and target queries into consideration without introducing heuristic expansion techniques. In addition, this paper reveals relationships between hyperspherical QLMs and conventional QLMs. Experiments show document retrieval evaluation results in which a hyperspherical QLM is compared to conventional QLMs and document distance metrics using word or document embeddings.</abstract>
<identifier type="citekey">masumura-etal-2017-hyperspherical</identifier>
<location>
<url>https://aclanthology.org/I17-2036/</url>
</location>
<part>
<date>2017-11</date>
<extent unit="page">
<start>210</start>
<end>216</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Hyperspherical Query Likelihood Models with Word Embeddings
%A Masumura, Ryo
%A Asami, Taichi
%A Masataki, Hirokazu
%A Sadamitsu, Kugatsu
%A Nishida, Kyosuke
%A Higashinaka, Ryuichiro
%Y Kondrak, Greg
%Y Watanabe, Taro
%S Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
%D 2017
%8 November
%I Asian Federation of Natural Language Processing
%C Taipei, Taiwan
%F masumura-etal-2017-hyperspherical
%X This paper presents an initial study on hyperspherical query likelihood models (QLMs) for information retrieval (IR). Our motivation is to naturally utilize pre-trained word embeddings for probabilistic IR. To this end, key idea is to directly leverage the word embeddings as random variables for directional probabilistic models based on von Mises-Fisher distributions which are familiar to cosine distances. The proposed method enables us to theoretically take semantic similarities between document and target queries into consideration without introducing heuristic expansion techniques. In addition, this paper reveals relationships between hyperspherical QLMs and conventional QLMs. Experiments show document retrieval evaluation results in which a hyperspherical QLM is compared to conventional QLMs and document distance metrics using word or document embeddings.
%U https://aclanthology.org/I17-2036/
%P 210-216
Markdown (Informal)
[Hyperspherical Query Likelihood Models with Word Embeddings](https://aclanthology.org/I17-2036/) (Masumura et al., IJCNLP 2017)
ACL
- Ryo Masumura, Taichi Asami, Hirokazu Masataki, Kugatsu Sadamitsu, Kyosuke Nishida, and Ryuichiro Higashinaka. 2017. Hyperspherical Query Likelihood Models with Word Embeddings. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 210–216, Taipei, Taiwan. Asian Federation of Natural Language Processing.