File Information
File: 05-lr/acl_arc_1_sum/cleansed_text/xml_by_section/intro/95/e95-1021_intro.xml
Size: 1,155 bytes
Last Modified: 2025-10-06 14:05:55
<?xml version="1.0" standalone="yes"?> <Paper uid="E95-1021"> <Title>and Arto Anttila (eds.). Constraint Grammar: a Language-Independent System for Parsing</Title> <Section position="4" start_page="0" end_page="0" type="intro"> <SectionTitle> 2 Morphological analysis and </SectionTitle> <Paragraph position="0"> guessing The morphological analyser is based on a lexical transducer (Karttunen et al., 1992). The transducer maps each inflected surface form of a word to its canonical lexical form followed by the appropriate morphological tags.</Paragraph> <Paragraph position="1"> Words not found in the lexicon are analysed by a separate finite-state transducer, the guesser. We developed a simple, extremely compact and efficient guesser for French. It is based on the general assumption that neologisms and uncommon words tend to follow regular inflectional patterns. The guesser is thus based on productive endings (like merit for adverbs, ible for adjectives, er for verbs). A given ending may of course point to various categories, e.g. er identifies nouns as well as verbs due to possible borrowings from English.</Paragraph> </Section> class="xml-element"></Paper>