Non-Literal Word Sense Identification Through Semantic Network Path Schemata
نویسندگان
چکیده
When computer programs disambiguate words in a sentence, they often encounter non-literal or novel usages not included in their lexicon. In a recent study, Georgia Green (personal communication) estimated that 17% to 20% of the content word senses encountered in various types of normal English text are not fisted in the dictionary. While these novel word senses are generally valid, they occur in such great numbers, and with such little individual frequency that it is impractical to explic i ty include them all within the lexicon. Instead, mechanisms are needed which can derive novel senses from existing ones; thus allowing a program to recognize a significant set of potential word senses while keeping its lexicon within a reasonable size.
منابع مشابه
Schemata-Building Role of Teaching Word History in Developing Reading Comprehension Ability
Methodologically, vocabulary instruction has faced significant ups and downs during the history of language education; sometimes integrated with the other elements of language network, other times tackled as a separate component. Among many variables supposedly affecting vocabulary achievement, the role of teaching word history, as a schemata-building strategy, in developing reading comprehensi...
متن کاملThe Mental Representation of Polysemy across Word Classes
Experimental studies on polysemy have come to contradictory conclusions on whether words with multiple senses are stored as separate or shared mental representations. The present study examined the semantic relatedness and semantic similarity of literal and non-literal (metonymic and metaphorical) senses of three word classes: nouns, verbs, and adjectives. Two methods were used: a psycholinguis...
متن کاملLiteral and Metaphorical Sense Identification through Concrete and Abstract Context
Metaphor is ubiquitous in text, even in highly technical text. Correct inference about textual entailment requires computers to distinguish the literal and metaphorical senses of a word. Past work has treated this problem as a classical word sense disambiguation task. In this paper, we take a new approach, based on research in cognitive linguistics that views metaphor as a method for transferri...
متن کاملA Clustering Approach for the Unsupervised Recognition of Nonliteral Language
In this thesis we present TroFi, a system for separating literal and nonliteral usages of verbs through unsupervised statistical word-sense disambiguation and clustering techniques. TroFi distinguishes itself by redefining the types of nonliteral language handled and by depending purely on sentential context rather than selectional constraint violations and paths in semantic hierarchies. TroFi ...
متن کاملA Clustering Approach for Nearly Unsupervised Recognition of Nonliteral Language
In this paper we present TroFi (Trope Finder), a system for automatically classifying literal and nonliteral usages of verbs through nearly unsupervised word-sense disambiguation and clustering techniques. TroFi uses sentential context instead of selectional constraint violations or paths in semantic hierarchies. It also uses literal and nonliteral seed sets acquired and cleaned without human s...
متن کامل