Sbdlrhmn: A rule-based human interpretation system for semantic textual similarity task

Samir AbdelRahman, Catherine Blake

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

Abstract

In this paper, we describe the system architecture used in the Semantic Textual Similarity (STS) task 6 pilot challenge. The goal of this challenge is to accurately identify five levels of semantic similarity between two sentences: equivalent, mostly equivalent, roughly equivalent, not equivalent but sharing the same topic and no equivalence. Our participations were two systems. The first system (rule-based) combines both semantic and syntax features to arrive at the overall similarity. The proposed rules enable the system to adequately handle domain knowledge gaps that are inherent when working with knowledge resources. As such one of its main goals, the system suggests a set of domain-free rules to help the human annotator in scoring semantic equivalence of two sentences. The second system is our baseline in which we use the Cosine Similarity between the words in each sentence pair.

Original languageEnglish (US)
Title of host publicationProceedings of the 6th International Workshop on Semantic Evaluation, SemEval 2012
PublisherAssociation for Computational Linguistics (ACL)
Pages536-542
Number of pages7
ISBN (Electronic)9781937284220
StatePublished - 2012
Event1st Joint Conference on Lexical and Computational Semantics, *SEM 2012 - Montreal, Canada
Duration: Jun 7 2012Jun 8 2012

Publication series

Name*SEM 2012 - 1st Joint Conference on Lexical and Computational Semantics
Volume2

Other

Other1st Joint Conference on Lexical and Computational Semantics, *SEM 2012
Country/TerritoryCanada
CityMontreal
Period6/7/126/8/12

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Theoretical Computer Science
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'Sbdlrhmn: A rule-based human interpretation system for semantic textual similarity task'. Together they form a unique fingerprint.

Cite this