Abstract for shih_tr170

Cambridge University Engineering Department Technical Report CUED/F-INFENG/TR170


Hsue-Hueh Shih and Steve Young

June 1994

A system of computer assisted grammar construction (CAGC) is presented in this report. The CAGC system is designed to generate broad-coverage grammars for large natural language corpora by utilizing both an extended inside-outside algorithm and an automatic phrase bracketing (AUTO) system which is designed to provide the extended algorithm with constituent information during learning. This paper demonstrates the capability of the CAGC system to deal with realistic natural language problems and the usefulness of the AUTO system in the inside-outside based grammar re-estimation. Performance results including the proportion of sentences parsed and precision are presented for a grammar constructed for the Wall Street Journal (WSJ) corpus.

(ftp:) shih_tr170.ps.Z (http:) shih_tr170.ps.Z
PDF (automatically generated from original PostScript document - may be badly aliased on screen):
  (ftp:) shih_tr170.pdf | (http:) shih_tr170.pdf

If you have difficulty viewing files that end '.gz', which are gzip compressed, then you may be able to find tools to uncompress them at the gzip web site.

If you have difficulty viewing files that are in PostScript, (ending '.ps' or '.ps.gz'), then you may be able to find tools to view them at the gsview web site.

We have attempted to provide automatically generated PDF copies of documents for which only PostScript versions have previously been available. These are clearly marked in the database - due to the nature of the automatic conversion process, they are likely to be badly aliased when viewed at default resolution on screen by acroread.