Semantic Co-occurrence Research Articles

On distribution of complementizers in contemporary Serbian

The paper investigates the principles governing the distribution of complementizers in contemporary Serbian. Evidence is presented that the distribution of da, sto, kako, gde, da li, and numerous interrogative pronouns and adverbials which may function as complementizers is determined not only by matrix-verb subcategorization properties and semantic co-occurrence restrictions which hold between the predicate and its complement, but by the lexical an syntactic properties of the particular verb class (or subclass) to which matrix predicate belongs as well. According to their ability to govern a particular complementizer, ten major verb subclasses are identified in contemporary Serbian, and their specific properties are signaled.

Consistent Criteria for Sense Distinctions

This paper specifically addresses the question of polysemy with respect to verbs, and whether or not the sense distinctions that are made in on-line lexical resources such as WordNet are appropriate for computational lexicons. The use of sets of related syntactic frames and verb classes are examined as a means of simplifying the task of defining different senses, and the importance of concrete criteria such as different predicate argument structures, semantic class constraints and lexical co-occurrences is emphasized.

Semantic co-occurrence filtering for speech recognition and signal transcription applications

A system and method for automatically transcribing an input question from a form convenient for user input into a form suitable for use by a computer. The question is a sequence of words represented in a form convenient for the user, such as a spoken utterance or a handwritten phrase. The question is transduced into a signal that is converted into a sequence of symbols. A set of hypotheses is generated from the sequence of symbols. The hypotheses are sequences of words represented in a form suitable for use by the computer, such as text. One or more information retrieval queries are constructed and executed to retrieve documents from a corpus (database). Retrieved documents are analyzed to produce an evaluation of the hypotheses of the set and to select one or more preferred hypotheses from the set. The preferred hypotheses are output to a display, speech synthesizer, or applications program. Additionally, retrieved documents relevant to the preferred hypotheses can be selected and output.

Language patterns of adolescent autistics.

The language samples of seven verbal autistic adolescents were analyzed. Linguistic deficits were compared to characteristics reported for preteen autistics and described structurally. Only four subjects demonstrated linguistic impairments. These clustered primarily in the area of prosodic features, semantic cooccurrence constraints and general disfluency. No such clustering had been reported for the preteen population. No correlation between linguistic deficits, IQ, and age was found. However, performance on the Seashore Test for Musical Ability correlated highly with linguistic performance. Results suggest that (a) autism includes liguistically, and possibly etiologically, distinct subtroups; (b) the basic linguistic deficits in autism may be more specific than thought previously; and (c) perception of prosodic features may be crucial for decoding and encoding linguistic signals. Autistic children may be lacking in this ability.

Meaning and meaning similarity. II. The semantic differential and co-occurrence as predictors of judged similarity in meaning.

Meaning and meaning similarity. II. The semantic differential and co-occurrence as predictors of judged similarity in meaning.