LANGUAGE IN INDIA

PARSING IN TAMIL: PRESENT STATE OF ART

S. Rajendran, Ph.D.

Parsing

Parsing is actually related to the automatic analysis of texts according to a grammar. Technically, it is used to refer to practice of assigning syntactic structure to a text. It is usually performed after basic morphosyntactic categories have been identified in a text. Based on different grammars parsing brings these morphosyntactic categories into higher-level syntactic relationships with one another. The survey of the state of art of parsing in Tamil reflects upon the global scenario. More or less the trends of the global arena in natural language processing are very much represented in Tamil too.

Overview of the Global Scenario

We try to understand larger textual units by combining our understanding of smaller ones. The linguistic theory aims to show how these larger units of meaning arise out of the combination of the smaller ones. This is modeled by means of a grammar. Computational linguistics then tries to implement this process in an efficient way. Traditionally the task is to subdivide into syntax and semantics; syntax describes how the different formal elements of a textual unit, most often the sentence, can be combined; semantics describes how the interpretation is calculated. In most language technology applications the encoded linguistic knowledge, i.e., the grammar, is separated from the processing components. The grammar consists of a lexicon, and rules that syntactically and semantically combine words and phrases into larger phrases and sentences.

A variety of representation languages have been developed for the encoding of linguistic knowledge. Some of these languages are more geared towards conformity with formal linguistic theories, others are designed to facilitate certain processing models or specialized applications. Several language technology products on the market today employ annotated phrase-structure grammars, grammars with several hundreds or thousands of rules describing different phrase types. Each of these rules is annotated by features, and sometimes also by expressions, in a programming language.

Current Research

In current research, a certain polarization has taken place. Very simple grammar models are employed, e.g., different kinds of finite-state grammars that support highly efficient processing. Some approaches do away with grammars altogether and use statistical methods to find basic linguistic patterns. On the other end of the scale, we find a variety of powerful linguistically sophisticated representation formalisms that facilitate grammar engineering. The most prevalent family of grammar formalisms currently used in computational linguistics is constraint based.

Morphological Analysis in Tamil

Tamil is a Dravidian language. It is a verb final, relatively free-word order and morphologically rich language. Like other Dravidian languages, Tamil is agglutinative. Computationally, each root word can take a few thousand inflected word-forms, out of which only a few hundred will exist in a typical corpus. Subject-verb argument is required for the grammaticality of a Tamil sentence. Tamil allows subject and object drop as well as verb less sentences. In addition, the subject of a sentence or a clause can be a possessive Noun Phrase (NP) or an NP in nominative or dative case. As Tamil is an agglutinative language, each root word can combine with multiple morphemes to generate word forms. For the purpose of analysis of such inflectionally rich languages, the root and the morphemes of each word has to be identified.

The global scenario has influenced the morphological analysis of Tamil. In the last decade, computational morphology has advanced further towards real-life applications than most other subfields of natural language processing. To build a syntactic representation of the input sentence, a parser must map each word in the text to some canonical representation and recognize its morphological properties. The combination of a surface form and its analysis as a canonical form and inflection is called a lemma. The main problems are:

1. Morphological alternations: the same morpheme may be realized in different ways depending on the context.
2. Morphotactics: stems, affixes, and parts of compounds do not combine freely, a morphological analyzer needs to know what arrangements are valid.

PLEASE CLICK HERE TO READ THE ENTIRE ARTICLE IN A PRINTER-FRIENDLY VERSION.

S. Rajendran

Communication Across Castes | The Hells Envisioned in the Divine Comedy and Bhagavtam | Telugu Parts of Speech Tagging in WSD | Practicing Literary Translation: A Symposium Round 10 | The Effectiveness of Genre-based Approach to Develop Writing Skills of Adult Learners and Its Significance for Designing a Syllabus | Structural Predictability of Malayalam Riddles | Parsing in Tamil - Present State of Art | HOME PAGE OF AUGUST 2006 ISSUE | HOME PAGE | CONTACT EDITOR