Informatics Publishing Limited

K. S. Sarath ¹, Manu V. Nair ¹, R. R. Rajeev ², P. C. Reghu Raj ¹

Affiliations
1 Department of CSE, Govt. Engineering College, Palakkad, Kerala, 678633, IN
2 VRCLC, IIITM-K, Trivandrum, Kerala, 695581, IN

Abstract

Dialect Resolution is a regional variety of language, with differences in vocabulary, grammar and pronunciation. It is recognized formal variant of the language spoken by a large group belonging to one region, class or profession. Dialect resolution is an approach to convert a dialect from an informal format to its formal format without losing its meaning. It is a localized approach through which a person can express idea in his own style and still be able to convert to a formal format. In this dialect resolution system, highly informal slang words are replaced by similar words in a given context. This paper presents a dialect resolution method that is a hybrid of Rule based and Machine learning approaches. This work concentrated on Thrissur dialect. Thrissur is a district of Kerala, which is well known for its distinguishable dialect variations.

Full Text

   

M. Anagha ¹, Raveena R. Kumar ¹, K. Sreetha ¹, R. R. Rajeev ², P. C. Reghu Raj ³

Affiliations
1 Computational Linguistics, Government Engineering College, Sreekrishnapuram, Palakkad, Kerala, IN
2 VRCLC, IIITM-K, Thiruvananthapuram, Kerala, IN
3 Dept. of Computer Science and Engineering, Government Engineering College, Sreekrishnapuram, Palakkad, Kerala, IN

Abstract

In this paper, Cross Domain Sentiment Analysis of Malayalam reviews is done by classifying the polarity of opinions obtained from the user as positive, negative and neutral. Sentiment analysis is an application of Natural Language Processing and text analysis which helps to identify the emotions in a given context. In this work a hybrid approach for Sentiment Analysis is used in which a Hindi Wordnet based lexical resource file is created which is used for finding polarity of review and Machine Learning method is used for tagging certain special cases. Certain other rules are also incorporated to handle special cases. The system yields output that varies in degree between 0 and 1.

Full Text

   

Alen Jacob ¹, Amal Babu ¹, R. R. Rajeev ², P. C. Reghu Raj ³

Affiliations
1 Computational Linguistics, Government Engineering College, Sreekrishnapuram, Palakkad, Kerala, IN
2 VRCLC, IIITM-K, Thiruvananthapuram, Kerala, IN
3 Dept. of Computer Science and Engineering, Government Engineering College, Sreekrishnapuram, Palakkad, Kerala, IN

Abstract

TnT is an efficient statistical Parts-of-speech (POS) Tagger based on Hidden Markov Model. TnT performs well on known word sequences. But, the performance degrades with increase in the number of unknown words. In this paper, we propose a method to overcome this performance degradation using fuzzy rules. Fuzzy rule based model is designed to provide TnT with sufficient information about the tag of unknown words without degrading the performance of TnT. On processing an unknown word from the input, the TnT tagger relies on the probability distribution of words having the same suffix within the training corpus. In Indian languages like Malayalam, the POS tag of an unknown word depends not only on suffix. Due to high inflectional and free order nature, the dependency is rather complex than the one captured by suffix tag distribution probabilities. When TnT with fuzzy rule based learning encounters an unknown word, the TnT generates a set of possible tags for the given word based on the fuzzy rules matched by the word. If the word does not match any fuzzy rule then the model depends upon the probability distribution of the suffix. This approach guarantees that the performance of TnT will only be improved from its normal performance.

Full Text