Language modeling using efficient best-first bottom-up parsing

Keith Hall, Mark Johnson

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

14 Citations (Scopus)

Abstract

In this paper we present a two-stage best-first bottom-up word-lattice parser which we use as a language model for speech recognition. The parser works by using a "Figure of Merit" that selects lattice paths while simultaneously selecting syntactic category edges for parsing. Additionally, we introduce a modified version of the Inside-Outside algorithm used as a pruning stage between syntactic context-free parsing and lexicalized context-dependent parsing. We report our results in terms of Word Error Rate on the HUB-1 word-lattices and compare these results to other syntactic language modeling techniques.

Original languageEnglish
Title of host publication2003 IEEE Workshop on Automatic Speech Recognition and Understanding
Place of PublicationPiscataway, NJ
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages507-512
Number of pages6
ISBN (Electronic)0780379802, 9780780379800
DOIs
Publication statusPublished - Dec 2003
Externally publishedYes
EventIEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2003 - St. Thomas, United States
Duration: 30 Nov 20034 Dec 2003

Other

OtherIEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2003
CountryUnited States
CitySt. Thomas
Period30/11/034/12/03

Fingerprint Dive into the research topics of 'Language modeling using efficient best-first bottom-up parsing'. Together they form a unique fingerprint.

  • Cite this

    Hall, K., & Johnson, M. (2003). Language modeling using efficient best-first bottom-up parsing. In 2003 IEEE Workshop on Automatic Speech Recognition and Understanding (pp. 507-512). [1318492] Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/ASRU.2003.1318492