Thumbnail
Access Restriction
Open

Author Antworth, Evan L.
Source CiteSeerX
Content type Text
File Format PDF
Language English
Subject Domain (in DDC) Computer science, information & general works ♦ Data processing & computer science
Subject Keyword Syntactic Parsing ♦ Kimmo Koskenniemi ♦ Natural Language Processing ♦ Standard Technique ♦ Past Tense Verb ♦ Syntactic Parser ♦ Likely Think ♦ Substantial Analysis ♦ Morphological Parser ♦ Parse Tree ♦ Inflectional Feature ♦ Singular Noun ♦ Complex Word ♦ Unification-based Word Grammar Component ♦ Two-level Morphology ♦ Morphological Parsing ♦ Unification-based Word Grammar ♦ Feature Structure
Description This paper describes PC-KIMMO, a morphological parser based on Kimmo Koskenniemi's model of two-level morphology (Koskenniemi 1983). While PC-KIMMO was adequate to decompose a word into morphemes, it was not able directly to compute the part of speech of a derivationally complex word or return a word's inflectional features--precisely the information required for syntactic parsing. These deficiencies have now been remedied by adding a unification-based word grammar component to version 2 of PC-KIMMO which can provide parse trees and feature structures. A substantial analysis of English for use with PC-KIMMO is also described. Why do morphological parsing? Parsing is a standard technique used in the field of natural language processing. When you think of parsing, you likely think of syntactic parsing. But before a syntactic parser can parse a sentence, it must be supplied with information about each word in the sentence. For instance, to parse the sentence The cat chased the rat, a parser must know that cat is a singular noun, chased is a past tense verb, and so on. In English, such
Educational Role Student ♦ Teacher
Age Range above 22 year
Educational Use Research
Education Level UG and PG ♦ Career/Technical Study
Learning Resource Type Article
Publisher Date 1994-01-01
Publisher Institution North Texas Natural Language Processing Workshop