Discovering Lexical Classes and Syntax: (Report with Annotated Bibliography)
نویسندگان
چکیده
In most of the languages today, the sequence of words is quite restricted. It is quite obvious that an underlying structure which is, in general, abstract, generates such word orders. This underlying structure is basically the syntax of the language. Also, it is shown in previous researches that syntactic features are the most informative features in lexical class discovery such as verb classification. We want to design a framework that will be unsupervised and can induce lexical classes and syntax from the given data. We may further want to extend this framework for languages such as Hindi which is poor in
منابع مشابه
Discovering Lexical Classes and Syntax using Word Embeddings (Report with Annotated Bibliography)
Word embeddings have the power to capture semantics.They have potential to represent syntax and semantics both. We have many sources of unsupervised raw data but not supervised data. Unsupervised techniques could greatly improve existing supervised (Collobert et al.(2013)). By leveraging large amount of data floating around, we can improve existing systems. We want to design a framework that wi...
متن کاملThe Comparative Impact of Pictorial Annotations and Morphological Instruction on Lexical Inferencing of Iranian Intermediate EFL Learners
One of the main ways to acquire unfamiliar words is to make guesses about words meaning. This study investigates the comparative effects of pictorial annotations and morphological instructions on Iranian EFL learners’ lexical inferencing ability. Considering homogeneity issues using PET (Preliminary English Test), the researchers assigned the participants into two experimental and one control g...
متن کاملDesign and Implementation of an Intelligent Part of Speech Generator
The aim of this paper is to report on an attempt to design and implement an intelligent system capable of generating the correct part of speech for a given sentence while the sentence is totally new to the system and not stored in any database available to the system. It follows the same steps a normal individual does to provide the correct parts of speech using a natural language processor. It...
متن کاملSafety-Critical Software: Status Report and Annotated Bibliography
Many systems are deemed safety-critical and these systems are increasingly dependent on software. Much has been written In the literature with respect to system and software safety. This repo~l sum;-,;A& .es some of that literature and outlines the development of saf,. criticai zcw,vare. Techniques for hazard identification and analysis are discussed. 'Further, techniques for the development of...
متن کاملDiscovering Semantic Classes for Urdu N-V Complex Predicates
This paper reports on an exploratory investigation as to whether classes of Urdu N-V complex predicates can be identified on the basis syntactic patterns and lexical choices associated with the N-V complex predicates. Working with data from a POS annotated corpus, we show that choices with respect to the number of arguments, case marking on subjects and which light verbs are felicitous with whi...
متن کامل