FASTUS is a system for extracting information from natural language text for entry into a database and for other applications. It works essentially as a cascaded, nondeterministic finite-state automaton. There are five stages in the operation of FASTUS. In Stage 1, names and other fixed form expressions are recognized. In Stage 2, basic noun groups, verb groups, and prepositions and some other ...

FASTUS is a system for extracting information from natural language text for entry into a database and for other applications. It works essentially as a cascaded, nondeterministic nite-state automaton. There are ve stages in the operation of FASTUS. In Stage 1, names and other xed form expressions are recognized. In Stage 2, basic noun groups, verb groups, and prepositions and some other partic...

We developed on example-based method of metonymy interpretation. One advantages of this method is that a hand-built database of metonymy is not necessary because it instead uses examples in the form \Noun X no Noun Y (Noun Y of Noun X)." Another advantage is that we will be able to interpret newly-coined metonymic sentences by using a new corpus. We experimented with metonymy interpretation and...

The issue of automatic processing of coordinate constructions (mainly NPs) with preand/or postmodifiers is investigated. The paper describes the CASSEX package which is capable of conjunction processing, illustrated with a group of English sentences containing modified coordinate NPs which are parsed and translated into Chinese by the package. 0. Introduction For a machine translation system to...

Psycholinguistic research demonstrates that representational distance between meanings influences recognition of ambiguous words. Our goal was to investigate whether the neural correlates of ambiguity are also modulated by representational distance as a function of syntactic similarity (i.e., grammatical class) and meaning dominance. In an event-related fMRI experiment, participants completed a...

Adjectives in Basaá [ɓasaá] (Bantu, A43: Cameroon) are morphologically nominal: they possess inherent noun class and distinguish singular and plural (Dimmendaal 1988, Hyman 2003). Additionally, adjectives in Basaá function as the head of their noun phrase, in a sense to be made precise below. This challenges the standard assumption that noun phrases or DPs are projected (or headed) by nouns. Th...

This paper presents an algorithm for selecting an appropriate classifier word for a noun. In Thai language, it frequently happens that there is fluctuation in the choice of classifier for a given concrete noun, both from the point of view of the whole speech community and individual speakers. Basically, there is no exact rule for classifier selection. As far as we can do in the rule-based appro...

We present the results of a study with six Serbo-Croatian-speaking agrammatic patients on a test of inflectional morphology in which subjects judged whether spoken sentences were grammatical or ungrammatical. Sensitivity to two kinds of syntactic features was investigated in these aphasic patients: (1) subcategorization rules for transitive verbs (which must be followed by a noun in the accusat...

A weakly-supervised method is applied to anonymized queries to extract lexical interpretations of compound noun phrases (e.g., “fortune 500 companies”). The interpretations explain the subsuming role (“listed in”) that modifiers (fortune 500) play relative to heads (companies) within the noun phrases. Experimental results over evaluation sets of noun phrases from multiple sources demonstrate th...

Parsing is a process of building structure onto a sentence or other string of characters so that the meaning of the sentence or string can be derived. Consider a simple English sentence: ”the boy hit the ball.” Thinking back to elementary school English class, the sentence can be broken into parts of speech as per Figure 1: an article followed by a noun, then a verb, then an article, then a nou...