Paper: Using The Web To Disambiguate Acronyms

ACL ID N06-2041
Title Using The Web To Disambiguate Acronyms
Venue Human Language Technologies
Session Short Paper
Year 2006
  • Eiichiro Sumita (National Institute of Information and Communications Technology, Kyoto Japan; ATR Spoken Language Communication Research Laboratories, Kyoto Japan)
  • Fumiaki Sugaya (KDDI R&D Labs, Saitama Japan)

This paper proposes an automatic method for disambiguating an acronym with mul- tiple definitions, considering the context surrounding the acronym. First, the method obtains the Web pages that in- clude both the acronym and its definitions. Second, the method feeds them to the ma- chine learner. Cross-validation tests re- sults indicate that the current accuracy of obtaining the appropriate definition for an acronym is around 92% for two ambigu- ous definitions and around 86% for five ambiguous definitions.