A fast and efficient semantic short text similarity metric

David Croft, Simon Coupland, Jethro Shell, Stephen Brown

Research output: Chapter in Book/Report/Conference proceedingConference proceedingpeer-review

24 Citations (Scopus)


The semantic comparison of short sections of text is an emerging aspect of Natural Language Processing (NLP). In this paper we present a novel Short Text Semantic Similarity (STSS) method, Lightweight Semantic Similarity (LSS), to address the issues that arise with sparse text representation. The proposed approach captures the semantic information contained when comparing text to process the similarity. The methodology combines semantic term similarities with a vector similarity method used within statistical analysis. A modification of the term vectors using synset similarity values addresses issues that are encountered with sparse text. LSS is shown to be comparable to current semantic similarity approaches, LSA and STASIS, whilst having a lower computational footprint.
Original languageEnglish
Title of host publication13th UK Workshop on Computational Intelligence (UKCI), 2013
Number of pages7
ISBN (Print)978­1­4799­1568­2
Publication statusPublished - 2013
Event13th UK Workshop on Computational Intelligence (UKCI) 2013 - University of Surrey, Guildford, United Kingdom
Duration: 9 Sep 201311 Sep 2013
Conference number: 13


Workshop13th UK Workshop on Computational Intelligence (UKCI) 2013
Abbreviated titleUKCI 2013
Country/TerritoryUnited Kingdom
Internet address


  • Vectors
  • Semantics
  • Measurment
  • Natural language processing
  • Educational institutions
  • Media
  • Electronic mail


Dive into the research topics of 'A fast and efficient semantic short text similarity metric'. Together they form a unique fingerprint.

Cite this