28.06.2013 Views

m - the Association for Computational Linguistics

m - the Association for Computational Linguistics

m - the Association for Computational Linguistics

SHOW MORE
SHOW LESS

You also want an ePaper? Increase the reach of your titles

YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.

Concordance<br />

J. H. Waite, R. Boehm, J. G. Fisher, S. D. Epstein, D. J. Stewart<br />

Cryptanalytic Computer Sciences Inc.<br />

Cherry Hill, N.J<br />

This study of <strong>the</strong> DDC Phrase Glossary includes a computer<br />

program to tabulate work frequencies <strong>for</strong> blocks of phrases of optional<br />

si,zes. On <strong>the</strong> basis of <strong>the</strong>se distributions, empirical and<br />

statistic~l analyses are made including two prediction models.<br />

Two-word distributions are also included. Based upon <strong>the</strong> available<br />

distributions, a two-word Phrase G1ossar.y size of 320,000 twoword<br />

phrases was determined. Also included are analyses of<br />

various techniques, such as suf,£ix truncation, imbedded phrases,<br />

and query effeotiveness. Comparisons are made of <strong>the</strong> DDC system<br />

to o<strong>the</strong>r plain lang~age machine retrieval systems. [AD-780 957/7GA<br />

PC $3.75, MF $1.45 April 19741<br />

J. L. Mitchell<br />

Computers in €he Humanities, J.L. Mitchell, Editor, 1974, 132-145<br />

As a necessary prerequisite to a syntactic investigation of<br />

<strong>the</strong> chronicle <strong>the</strong> £011 owing ana lyses are p roduced : alphabetized<br />

list of every w o ~ d of <strong>the</strong> corpu S, cum ulati ve freq uency , alphabetized<br />

frequency list , rank of every word , cumul ative absolute<br />

freguenc.~ of every group of words, percentage and cumulative frequency<br />

of <strong>the</strong> text represented by each word and group of words,<br />

a concor"dance, a frequency list <strong>for</strong> grammatical categories, and<br />

<strong>the</strong> text with each word tagged <strong>for</strong> syntactic category.

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!