Broohm: Noun Classification in Esahie
نویسندگان
چکیده
منابع مشابه
Classification of Noun-Noun Compound Semantics in Dutch and Afrikaans
This article presents initial results on a supervised machine learning approach to determine the semantics of noun compounds in Dutch and Afrikaans. After a discussion of previous research on the topic, we present our annotation methods used to provide a training set of compounds with the appropriate semantic class. The support vector machine method used for this classification experiment utili...
متن کاملClassification in combined phrases: noun-noun conjunctions and intersective, subsective and privative adjective-noun combinations
How is the meaning of an adjectivenoun phrase related to the meanings of its adjective and noun constituents? Different types of adjective produce different relations between a combination and in its constituent adjectives and nouns. Current theories give separate mechanisms for each adjective type. This paper shows how a computational model originally developed to explain classification in nou...
متن کاملThe unaccusative hypothesis and noun classification*
The unaccusative hypothesis of Perlmutter (1978) andBurzio (1981,1986) claims that intransitive verbs are not homogeneous; rather, they are divided into two classes: unergative and unaccusative. This paper argues that the unaccusative hypothesis can be extended to the category of noun. Evidence supporting this claim comes from the resultative construction and accusative-case assignment in Japan...
متن کاملVerb Noun Construction MWE Token Classification
We address the problem of classifying multiword expression tokens in running text. We focus our study on Verb-Noun Constructions (VNC) that vary in their idiomaticity depending on context. VNC tokens are classified as either idiomatic or literal. We present a supervised learning approach to the problem. We experiment with different features. Our approach yields the best results to date on MWE c...
متن کاملNoun Classification from Predicate-Argument Structures
A method of determining the similarity of nouns on the basis of a metric derived from the distribution of subject, verb and object in a large text corpus is described. The resulting quasi-semantic classification of nouns demonstrates the plausibility of the distributional hypothesis, and has potential application to a variety of tasks, including automatic indexing, resolving nominal compounds, ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Ghana Journal of Linguistics
سال: 2017
ISSN: 2026-6596
DOI: 10.4314/gjl.v6i3.4