File Information

File: 05-lr/acl_arc_1_sum/cleansed_text/xml_by_section/concl/94/c94-1081_concl.xml

Size: 2,068 bytes

Last Modified: 2025-10-06 13:57:08

<?xml version="1.0" standalone="yes"?>
<Paper uid="C94-1081">
  <Title>PARSING TURKISH USING THE LEXICAL FUNCTIONAL GRAMMAR FORMALISM 1</Title>
  <Section position="8" start_page="499" end_page="499" type="concl">
    <SectionTitle>
7 CONCLUSIONS AND SUGGESTIONS
</SectionTitle>
    <Paragraph position="0"> We have presented a summary and highlights of our current work on providing an LFG specilication for Turkish syntax. To the best of our knowledge this is the tirst such effort for constructing a computational grammar for Tnrkish. Our domain includes structurally simple and complex Turkish sentences. The rather complex morphological analyses of agglutinative words structures of Turkish are handled by a full-scale two-level morphological specitication implemented in PC-KIMMO.</Paragraph>
    <Paragraph position="1"> We have number of directions for improving our grammar and parser: * Turkish is very rich in terms of adverbial constructs.</Paragraph>
    <Paragraph position="2"> We handle a great deal of these constructs by using a large number of rules. We are now in the process of developing a tagger with a multi-word construct recognizer to preprocess the text so that many multi-word and idiomatic constructs can he handled outside the grammar. In this way, multi-word constructs such as yapar yapmaz (do+AOR+3SG do+NEG+AOR+3SG) (as soon as (one) does (that)) where both lexical categories are verbal but the coml~ound construct is an adverb, can be handled, so can idiomatic constructs like yant stra (side+3SG-POSS row) (besides) where the flmction and semantics of the multi-word construct has nothing to do with the function and semantics of the constituent lexical tbrms.</Paragraph>
    <Paragraph position="3"> * We are currently working on extending the subset of sentences dealt with in respect of structure.</Paragraph>
    <Paragraph position="4"> * We are currently working on augmenting our lexicon with substantial lexical information and selectional restriction information to be used with an integrated ontological database.</Paragraph>
  </Section>
class="xml-element"></Paper>
Download Original XML