Inferring Semantics from Collocation Clusters to Represent Verbs and Nouns
نویسنده
چکیده
Current lexical semantic theories provide representations at a coarse grained level. In this paper, I will provide motivations for a fine grained representation for verbs and. nouns. An initial case study is done to serve as evidence that a more detailed representation is needed for tasks that require high accuracy rates, such as machine translation. An automatic approach to gather fine grained information via corpus extraction is described. Lastly, issues of lexical representation and cross-lingual translation are discussed.
منابع مشابه
Developing a Semantic Similarity Judgment Test for Persian Action Verbs and Non-action Nouns in Patients With Brain Injury and Determining its Content Validity
Objective: Brain trauma evidences suggest that the two grammatical categories of noun and verb are processed in different regions of the brain due to differences in the complexity of grammatical and semantic information processing. Studies have shown that the verbs belonging to different semantic categories lead to neural activity in different areas of the brain, and action verb processing is r...
متن کاملSeeing Arguments through Transparent Structures
This paper describes a research effort that exploits information available in the FrameNet database and seeks to find, for argumentstructure-bearing verbs, nouns, and adjectives, the lexical heads of the phrases that satisfy the core semantic roles of those predicates, and to create from the database of annotated sentences collections of structured clusters of words, called kernel dependency gr...
متن کاملآسیبپذیری افتراقی اسم و فعل در بیماران زبانپریش
Objectives : the study was designed to investigate the impairment of the ability to discriminate between nouns and verbs, resulting from the damage to the left-hemisphere, a condition which could lead to linguistic disorders proportionate to the depth and extent of the damage. Various experimental and clinical investigations have demonstrated that nouns and verbs may, independent of one anoth...
متن کاملEvents and the ontology of individuals : verbs as a source of individuating nouns
We explored the mapping between mass-count syntax and semantics, and how verb event semantics affect the meaning of derived nouns. In Experiment 1, we compared the interpretation of mass and count nouns derived from iterative verbs that describe bounded events (e.g., jump) and nouns derived from non-iterative verbs that describe unbounded events (e.g., dance). Participants based judgments prima...
متن کاملLearning description of term patterns using glossary resources
In this paper, we describe a method of automatic extraction of knowledge patterns using in term descriptions from glossary, and using them to extract term description from technical texts. A brief introduction of the problem will be presented. After that, knowledge patterns and related works are discussed. By statistical analysis, we will show that these patterns can be learned, and we will pro...
متن کامل