Semantic convolution kernels over dependency trees: Smoothed partial tree kernel

Danilo Croce, Alessandro Moschitti, Roberto Basili

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Citations (Scopus)

Abstract

In recent years, natural language processing techniques have been used more and more in IR. Among other syntactic and semantic parsing are effective methods for the design of complex applications like for example question answering and sentiment analysis. Unfortunately, extracting feature representations suitable for machine learning algorithms from linguistic structures is typically difficult. In this paper, we describe one of the most advanced piece of technology for automatic engineering of syntactic and semantic patterns. This method merges together convolution dependency tree kernels with lexical similarities. It can efficiently and effectively measure the similarity between dependency structures, whose lexical nodes are in part or completely different. Its use in powerful algorithm such as Support Vector Machines (SVMs) allows for fast design of accurate automatic systems. We report some experiments on question classification, which show an unprecedented result, e.g. 41% of error reduction of the former state-of-the-art, along with the analysis of the nice properties of the approach.

Original languageEnglish
Title of host publicationInternational Conference on Information and Knowledge Management, Proceedings
Pages2013-2016
Number of pages4
DOIs
Publication statusPublished - 13 Dec 2011
Externally publishedYes
Event20th ACM Conference on Information and Knowledge Management, CIKM'11 - Glasgow, United Kingdom
Duration: 24 Oct 201128 Oct 2011

Other

Other20th ACM Conference on Information and Knowledge Management, CIKM'11
CountryUnited Kingdom
CityGlasgow
Period24/10/1128/10/11

Fingerprint

Kernel
Convolution
Natural language processing
Node
Support vector machine
Sentiment analysis
Experiment
Question answering
Machine learning
Learning algorithm

Keywords

  • kernel methods
  • natural language processing
  • question answering
  • support vector machines
  • syntactic semantic structures

ASJC Scopus subject areas

  • Business, Management and Accounting(all)
  • Decision Sciences(all)

Cite this

Croce, D., Moschitti, A., & Basili, R. (2011). Semantic convolution kernels over dependency trees: Smoothed partial tree kernel. In International Conference on Information and Knowledge Management, Proceedings (pp. 2013-2016) https://doi.org/10.1145/2063576.2063878

Semantic convolution kernels over dependency trees : Smoothed partial tree kernel. / Croce, Danilo; Moschitti, Alessandro; Basili, Roberto.

International Conference on Information and Knowledge Management, Proceedings. 2011. p. 2013-2016.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Croce, D, Moschitti, A & Basili, R 2011, Semantic convolution kernels over dependency trees: Smoothed partial tree kernel. in International Conference on Information and Knowledge Management, Proceedings. pp. 2013-2016, 20th ACM Conference on Information and Knowledge Management, CIKM'11, Glasgow, United Kingdom, 24/10/11. https://doi.org/10.1145/2063576.2063878
Croce D, Moschitti A, Basili R. Semantic convolution kernels over dependency trees: Smoothed partial tree kernel. In International Conference on Information and Knowledge Management, Proceedings. 2011. p. 2013-2016 https://doi.org/10.1145/2063576.2063878
Croce, Danilo ; Moschitti, Alessandro ; Basili, Roberto. / Semantic convolution kernels over dependency trees : Smoothed partial tree kernel. International Conference on Information and Knowledge Management, Proceedings. 2011. pp. 2013-2016
@inproceedings{bce36e1206f04e2498da71a24de4fede,
title = "Semantic convolution kernels over dependency trees: Smoothed partial tree kernel",
abstract = "In recent years, natural language processing techniques have been used more and more in IR. Among other syntactic and semantic parsing are effective methods for the design of complex applications like for example question answering and sentiment analysis. Unfortunately, extracting feature representations suitable for machine learning algorithms from linguistic structures is typically difficult. In this paper, we describe one of the most advanced piece of technology for automatic engineering of syntactic and semantic patterns. This method merges together convolution dependency tree kernels with lexical similarities. It can efficiently and effectively measure the similarity between dependency structures, whose lexical nodes are in part or completely different. Its use in powerful algorithm such as Support Vector Machines (SVMs) allows for fast design of accurate automatic systems. We report some experiments on question classification, which show an unprecedented result, e.g. 41{\%} of error reduction of the former state-of-the-art, along with the analysis of the nice properties of the approach.",
keywords = "kernel methods, natural language processing, question answering, support vector machines, syntactic semantic structures",
author = "Danilo Croce and Alessandro Moschitti and Roberto Basili",
year = "2011",
month = "12",
day = "13",
doi = "10.1145/2063576.2063878",
language = "English",
isbn = "9781450307178",
pages = "2013--2016",
booktitle = "International Conference on Information and Knowledge Management, Proceedings",

}

TY - GEN

T1 - Semantic convolution kernels over dependency trees

T2 - Smoothed partial tree kernel

AU - Croce, Danilo

AU - Moschitti, Alessandro

AU - Basili, Roberto

PY - 2011/12/13

Y1 - 2011/12/13

N2 - In recent years, natural language processing techniques have been used more and more in IR. Among other syntactic and semantic parsing are effective methods for the design of complex applications like for example question answering and sentiment analysis. Unfortunately, extracting feature representations suitable for machine learning algorithms from linguistic structures is typically difficult. In this paper, we describe one of the most advanced piece of technology for automatic engineering of syntactic and semantic patterns. This method merges together convolution dependency tree kernels with lexical similarities. It can efficiently and effectively measure the similarity between dependency structures, whose lexical nodes are in part or completely different. Its use in powerful algorithm such as Support Vector Machines (SVMs) allows for fast design of accurate automatic systems. We report some experiments on question classification, which show an unprecedented result, e.g. 41% of error reduction of the former state-of-the-art, along with the analysis of the nice properties of the approach.

AB - In recent years, natural language processing techniques have been used more and more in IR. Among other syntactic and semantic parsing are effective methods for the design of complex applications like for example question answering and sentiment analysis. Unfortunately, extracting feature representations suitable for machine learning algorithms from linguistic structures is typically difficult. In this paper, we describe one of the most advanced piece of technology for automatic engineering of syntactic and semantic patterns. This method merges together convolution dependency tree kernels with lexical similarities. It can efficiently and effectively measure the similarity between dependency structures, whose lexical nodes are in part or completely different. Its use in powerful algorithm such as Support Vector Machines (SVMs) allows for fast design of accurate automatic systems. We report some experiments on question classification, which show an unprecedented result, e.g. 41% of error reduction of the former state-of-the-art, along with the analysis of the nice properties of the approach.

KW - kernel methods

KW - natural language processing

KW - question answering

KW - support vector machines

KW - syntactic semantic structures

UR - http://www.scopus.com/inward/record.url?scp=83055186787&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=83055186787&partnerID=8YFLogxK

U2 - 10.1145/2063576.2063878

DO - 10.1145/2063576.2063878

M3 - Conference contribution

AN - SCOPUS:83055186787

SN - 9781450307178

SP - 2013

EP - 2016

BT - International Conference on Information and Knowledge Management, Proceedings

ER -