Content area
Full Text
Abstract- The aim of this work is to design and implement a system to identify, analyze and tag the constituents in the sentence which fill a semantic role expressed by some target verbs of a sentence in Tamil. The system reads a Tamil text document and performs tagging of semantic roles associated with a given target verb such as Agent, Patient, Instrument, etc. and also adjuncts such as Locative, Temporal, Manner, Cause, etc. within such a document using a hybrid approach by considering syntactic, semantic, and statistical evidence in the sentences. It consists of two main phases-a Learning Phase and an Evaluation Phase. The Learning phase consists of two main components namely a Maximum Entropy Model (MEM) and a Learning Component. The Evaluation Phase consists of four main components namely MEM Evaluator, Verb Frame Invoker, Rule Based Probability Assigner and Expectation Maximizer Component. A number of different performance measures are charted and the performance of the system is judged on the criteria of accuracy, ambiguity in labeling and how the labeling was performed.
Index Terms- semantic role, Maximum entropy model, expectation-maximization
(ProQuest: ... denotes formulae omitted.)
I. INTRODUCTION
Tamil language follows a partial free word order. Due to this property purely statistical approach is not hold good for Tamil. As like most Indian languages, Tamil is heavily conjugated, and hence lemmatization is a difficult task. Incomplete Heuristics Rules can never be complete. Hence a purely heuristic approach won't work. The word order and to an extent the grammatical structure is semantically oriented which means that they depend on the meaning conveyed. Generally Semantic roles are identified as "the underlying relation that a constituent has with the main verb in a clause". The problem of Semantic Role Labeling was identified as a crucial NLP task which was essential for many applications like answering questions in Information Extraction, Question Answering, Summarization, and, in general, in all NLP tasks in which some kind of semantic interpretation is needed. The Shared Tasks of CoNLL 2004 and CoNLL 2005 defined the task of Semantic Role Labeling as "analyzing the propositions expressed by some target verbs of the sentence. In particular, for each target verb all the constituents in the sentence which fill a semantic role of the verb...