@inproceedings{nikolentzos-etal-2017-shortest,
title = "Shortest-Path Graph Kernels for Document Similarity",
author = "Nikolentzos, Giannis and
Meladianos, Polykarpos and
Rousseau, Fran{\c{c}}ois and
Stavrakas, Yannis and
Vazirgiannis, Michalis",
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/D17-1202",
doi = "10.18653/v1/D17-1202",
pages = "1890--1900",
abstract = "In this paper, we present a novel document similarity measure based on the definition of a graph kernel between pairs of documents. The proposed measure takes into account both the terms contained in the documents and the relationships between them. By representing each document as a graph-of-words, we are able to model these relationships and then determine how similar two documents are by using a modified shortest-path graph kernel. We evaluate our approach on two tasks and compare it against several baseline approaches using various performance metrics such as DET curves and macro-average F1-score. Experimental results on a range of datasets showed that our proposed approach outperforms traditional techniques and is capable of measuring more accurately the similarity between two documents.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nikolentzos-etal-2017-shortest">
<titleInfo>
<title>Shortest-Path Graph Kernels for Document Similarity</title>
</titleInfo>
<name type="personal">
<namePart type="given">Giannis</namePart>
<namePart type="family">Nikolentzos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Polykarpos</namePart>
<namePart type="family">Meladianos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">François</namePart>
<namePart type="family">Rousseau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yannis</namePart>
<namePart type="family">Stavrakas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michalis</namePart>
<namePart type="family">Vazirgiannis</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>In this paper, we present a novel document similarity measure based on the definition of a graph kernel between pairs of documents. The proposed measure takes into account both the terms contained in the documents and the relationships between them. By representing each document as a graph-of-words, we are able to model these relationships and then determine how similar two documents are by using a modified shortest-path graph kernel. We evaluate our approach on two tasks and compare it against several baseline approaches using various performance metrics such as DET curves and macro-average F1-score. Experimental results on a range of datasets showed that our proposed approach outperforms traditional techniques and is capable of measuring more accurately the similarity between two documents.</abstract>
<identifier type="citekey">nikolentzos-etal-2017-shortest</identifier>
<identifier type="doi">10.18653/v1/D17-1202</identifier>
<location>
<url>https://aclanthology.org/D17-1202</url>
</location>
<part>
<date>2017-09</date>
<extent unit="page">
<start>1890</start>
<end>1900</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Shortest-Path Graph Kernels for Document Similarity
%A Nikolentzos, Giannis
%A Meladianos, Polykarpos
%A Rousseau, François
%A Stavrakas, Yannis
%A Vazirgiannis, Michalis
%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 nikolentzos-etal-2017-shortest
%X In this paper, we present a novel document similarity measure based on the definition of a graph kernel between pairs of documents. The proposed measure takes into account both the terms contained in the documents and the relationships between them. By representing each document as a graph-of-words, we are able to model these relationships and then determine how similar two documents are by using a modified shortest-path graph kernel. We evaluate our approach on two tasks and compare it against several baseline approaches using various performance metrics such as DET curves and macro-average F1-score. Experimental results on a range of datasets showed that our proposed approach outperforms traditional techniques and is capable of measuring more accurately the similarity between two documents.
%R 10.18653/v1/D17-1202
%U https://aclanthology.org/D17-1202
%U https://doi.org/10.18653/v1/D17-1202
%P 1890-1900
Markdown (Informal)
[Shortest-Path Graph Kernels for Document Similarity](https://aclanthology.org/D17-1202) (Nikolentzos et al., EMNLP 2017)
ACL
- Giannis Nikolentzos, Polykarpos Meladianos, François Rousseau, Yannis Stavrakas, and Michalis Vazirgiannis. 2017. Shortest-Path Graph Kernels for Document Similarity. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 1890–1900, Copenhagen, Denmark. Association for Computational Linguistics.