Learning paraphrase identification with structural alignment

Liang Chen, Praveen Paritosh, Vinodh Rajendran, Kenneth D Forbus

Research output: Contribution to journalConference article

6 Citations (Scopus)

Abstract

Semantic similarity of text plays an important role in many NLP tasks. It requires using both local information like lexical semantics and structural information like syntactic structures. Recent progress in word representation provides good resources for lexical semantics, and advances in natural language analysis tools make it possible to efficiently generate syntactic and semantic annotations. However, how to combine them to capture the semantics of text is still an open question. Here, we propose a new alignment-based approach to learn semantic similarity. It uses a hybrid representation, attributed relational graphs, to encode lexical, syntactic and semantic information. Alignment of two such graphs combines local and structural information to support similarity estimation. To improve alignment, we introduced structural constraints inspired by a cognitive theory of similarity and analogy. Usually only similarity labels are given in training data and the true alignments are unknown, so we address the learning problem using two approaches: alignment as feature extraction and alignment as latent variable. Our approach is evaluated on the paraphrase identification task and achieved results competitive with the state-of-theart. 1 Intr.

Original languageEnglish (US)
Pages (from-to)2859-2865
Number of pages7
JournalIJCAI International Joint Conference on Artificial Intelligence
Volume2016-January
StatePublished - Jan 1 2016
Event25th International Joint Conference on Artificial Intelligence, IJCAI 2016 - New York, United States
Duration: Jul 9 2016Jul 15 2016

Fingerprint

Semantics
Syntactics
Feature extraction
Labels

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Chen, Liang ; Paritosh, Praveen ; Rajendran, Vinodh ; Forbus, Kenneth D. / Learning paraphrase identification with structural alignment. In: IJCAI International Joint Conference on Artificial Intelligence. 2016 ; Vol. 2016-January. pp. 2859-2865.
@article{9bf66e4a7f284139a26f4eeb659d3e7b,
title = "Learning paraphrase identification with structural alignment",
abstract = "Semantic similarity of text plays an important role in many NLP tasks. It requires using both local information like lexical semantics and structural information like syntactic structures. Recent progress in word representation provides good resources for lexical semantics, and advances in natural language analysis tools make it possible to efficiently generate syntactic and semantic annotations. However, how to combine them to capture the semantics of text is still an open question. Here, we propose a new alignment-based approach to learn semantic similarity. It uses a hybrid representation, attributed relational graphs, to encode lexical, syntactic and semantic information. Alignment of two such graphs combines local and structural information to support similarity estimation. To improve alignment, we introduced structural constraints inspired by a cognitive theory of similarity and analogy. Usually only similarity labels are given in training data and the true alignments are unknown, so we address the learning problem using two approaches: alignment as feature extraction and alignment as latent variable. Our approach is evaluated on the paraphrase identification task and achieved results competitive with the state-of-theart. 1 Intr.",
author = "Liang Chen and Praveen Paritosh and Vinodh Rajendran and Forbus, {Kenneth D}",
year = "2016",
month = "1",
day = "1",
language = "English (US)",
volume = "2016-January",
pages = "2859--2865",
journal = "IJCAI International Joint Conference on Artificial Intelligence",
issn = "1045-0823",

}

Learning paraphrase identification with structural alignment. / Chen, Liang; Paritosh, Praveen; Rajendran, Vinodh; Forbus, Kenneth D.

In: IJCAI International Joint Conference on Artificial Intelligence, Vol. 2016-January, 01.01.2016, p. 2859-2865.

Research output: Contribution to journalConference article

TY - JOUR

T1 - Learning paraphrase identification with structural alignment

AU - Chen, Liang

AU - Paritosh, Praveen

AU - Rajendran, Vinodh

AU - Forbus, Kenneth D

PY - 2016/1/1

Y1 - 2016/1/1

N2 - Semantic similarity of text plays an important role in many NLP tasks. It requires using both local information like lexical semantics and structural information like syntactic structures. Recent progress in word representation provides good resources for lexical semantics, and advances in natural language analysis tools make it possible to efficiently generate syntactic and semantic annotations. However, how to combine them to capture the semantics of text is still an open question. Here, we propose a new alignment-based approach to learn semantic similarity. It uses a hybrid representation, attributed relational graphs, to encode lexical, syntactic and semantic information. Alignment of two such graphs combines local and structural information to support similarity estimation. To improve alignment, we introduced structural constraints inspired by a cognitive theory of similarity and analogy. Usually only similarity labels are given in training data and the true alignments are unknown, so we address the learning problem using two approaches: alignment as feature extraction and alignment as latent variable. Our approach is evaluated on the paraphrase identification task and achieved results competitive with the state-of-theart. 1 Intr.

AB - Semantic similarity of text plays an important role in many NLP tasks. It requires using both local information like lexical semantics and structural information like syntactic structures. Recent progress in word representation provides good resources for lexical semantics, and advances in natural language analysis tools make it possible to efficiently generate syntactic and semantic annotations. However, how to combine them to capture the semantics of text is still an open question. Here, we propose a new alignment-based approach to learn semantic similarity. It uses a hybrid representation, attributed relational graphs, to encode lexical, syntactic and semantic information. Alignment of two such graphs combines local and structural information to support similarity estimation. To improve alignment, we introduced structural constraints inspired by a cognitive theory of similarity and analogy. Usually only similarity labels are given in training data and the true alignments are unknown, so we address the learning problem using two approaches: alignment as feature extraction and alignment as latent variable. Our approach is evaluated on the paraphrase identification task and achieved results competitive with the state-of-theart. 1 Intr.

UR - http://www.scopus.com/inward/record.url?scp=85006091199&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85006091199&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85006091199

VL - 2016-January

SP - 2859

EP - 2865

JO - IJCAI International Joint Conference on Artificial Intelligence

JF - IJCAI International Joint Conference on Artificial Intelligence

SN - 1045-0823

ER -