<?xml version="1.0" standalone="yes"?>
<Paper uid="J79-1036">
  <Title>Grammatical Compression in Notes and Records: Analysis and Cornputdtion Barbara B. Anderson, Irwin D. J. Bross, and</Title>
  <Section position="16" start_page="116" end_page="116" type="concl">
    <SectionTitle>
Parsing Results
</SectionTitle>
    <Paragraph position="0"> Parsing output is in the form of a tree, illustrated for a typicdl fragment in Fig. 1. (Only the nodes mentioned above are shown, plus LN/RN = left/  right modifiers of Noun,) The full power of the parser is better illustrated by  -- null the along full sentences; but space does not permit presenting them here. Fig. 1 Parse tree for FRAGMENT = 5-2-67 chest--no chanqe sjnce 2-7-67 FRAGMENT.</Paragraph>
    <Paragraph position="1"> A summary of the parsing results is given in Table 4. Of the total 245 sentences, a correct firat parse was obtained for 171 or 69.8%, and a first parse adequate for further processing to obtain an &amp;quot;information format1' in 213 cases, or 86.9%. The latter statement brings us to the important question of how these parses are to be used.</Paragraph>
    <Paragraph position="2">  The aim in processing natural language notes and records is to arrive at forms for the data which are suitable for computerized information retrieval. The data structures must not change the meaning. This is why syntactic methods are knpo%ant. Parsing with an English grammar provides the gross structure of input sentences. (The use of English transformations makes the grammatical analysis more refined,) In each specialized technical area, more specific structure is p~s~ibie, making use of the restricted word usage characteristic of the disqourse in the given subject area.</Paragraph>
    <Paragraph position="3"> K) A second stage of processing of this type is now being applied to the parsed corpus of medical records and will be reported in a subsequent paper. A convenkent test of the adeqyacy of the parsing outputs is therefore whether they can serve as input to this second stage of processing (called forhatting). It can be seen in Table 4 that a number of &amp;quot;wrong&amp;quot; parses were still adequate as input to the formatting; the segmentation of the sentence into parts was correct even if the parts were assigned an incorrect syntactic status, e.g., object instead of adjunct. Only when the first parse was not adequate for formatting was the sentence rerun to obtain alternative analyses.</Paragraph>
    <Paragraph position="4"> The parsing times are a rough indication of the efficiency of the parsing but two points should be kept in mind. (1) The present LSP system is not a production model, but a research tool, with all that implies. (2) A bignificant fraction of the input sentences were &amp;quot;no data&amp;quot; types, e,g., None this visit. These word sequences were so limited linguistically that a literal formula could serve to reaogniae them. The experimental use of such a formula cut down parsing times on the no-data entries from about 1.817 to0.030. However, this formula was not used in the parsing summarized in Table 4, - This investigation was supported by Public Health service Research Grant number CA-11531 from the National Cancer Institute.</Paragraph>
    <Paragraph position="5"> losee Ref. 5 and A. Sager, Syntactic Formatting of Scientific Information, Proc. FJCC, AFIPS Press, Montvale, N. J., 1972,</Paragraph>
  </Section>
class="xml-element"></Paper>