Class-based collocations for Word Sense Disambiguation
نویسندگان
چکیده
This paper describes the NMSU-Pitt-UNCA word-sense disambiguation system participating in the Senseval-3 English lexical sample task. The focus of the work is on using semantic class-based collocations to augment traditional word-based collocations. Three separate sources of word relatedness are used for these collocations: 1) WordNet hypernym relations; 2) cluster-based word similarity classes; and 3) dictionary definition analysis.
منابع مشابه
Preposition Semantic Classification via Treebank and FrameNet
This paper reports on experiments in classifying the semantic role annotations assigned to prepositional phrases in both PENN TREEBANK (version II) and FRAMENET (version 0.75). In both cases, experiments are done to see how the prepositions can be classified given the dataset’s role inventory, using standard word-sense disambiguation features, such as the parts of speech of surrounding words, a...
متن کاملHITSZ_CITYU: Combine Collocation, Context Words and Neighboring Sentence Sentiment in Sentiment Adjectives Disambiguation
This paper presents the HIT_CITYU systems in Semeval-2 Task 18, namely, disambiguating sentiment ambiguous adjectives. The baseline system (HITSZ_CITYU_3) incorporates bi-gram and n-gram collocations of sentiment adjectives, and other context words as features in a one-class Support Vector Machine (SVM) classifier. To enhance the baseline system, collocation set expansion and characteristics le...
متن کامل15 . Collocations
This chapter describes a class of word groups that lies between idioms and free word combinations. Idiomatic expressions are those in which the semantics of the whole cannot be deduced from the meanings of the individual constituents. Free word combinations have the properties that each of the words can be replaced by another without seriously modifying the overall meaning of the composite unit...
متن کاملRecognition of Structured Collocations in An Inflective Language
We present a method of the structural collocations extraction for an inflective language (Polish) based on the process divided into two phases: extraction and filtering of the pairs of wordforms reduced to baseforms and structural annotation of the extracted collocations with lexico-syntactic patterns. The parameters of the patterns are specified manually but their instances are generated and t...
متن کاملOne Sense per Collocation and Genre/Topic Variations
This paper revisits the one sense per collocation hypothesis using fine-grained sense distinctions and two different corpora. We show that the hypothesis is weaker for fine-grained sense distinctions (70% vs. 99% reported earlier on 2-way ambiguities). We also show that one sense per collocation does hold across corpora, but that collocations vary from one corpus to the other, following genre a...
متن کامل