International Journal of Computer Processing of Languages

This paper reports about the development of a Named Entity Recognition (NER) system in Indian languages, particularly for Bengali, Hindi, Telugu, Oriya and Urdu using the statistical Maximum Entropy (ME) framework. We have used the annotated corpora, obtained from the IJCNLP-08 NER Shared Task for South and South East Asian Languages (NERSSEAL) and tagged with the twelve NE tags. An appropriate tag conversion routine has been developed in order to convert these corpora to the forms, tagged with four NE tags, namely Person name, Location name, Organization name and Miscellaneous name. The system makes use of the different contextual information of the words along with the variety of orthographic word-level features that are helpful in predicting the four NE classes. In this work, we have considered language independent features as well as language specific features. Language independent features include the contextual words, prefixes and suffixes of all the words in the training corpus, several digit features depending upon the presence and/or the number of digits in a token, first word of the sentence and the frequency features of the words. The system considers linguistic features, particularly for Bengali and Hindi. Linguistic features of Bengali include the set of known suffixes that may appear with NEs, clue words that help in predicting the location and organization names, words that help to recognize measurement expressions, designation words that help to identify person names, various gazetteer lists like the first names, middle names, last names, location names, organization names, function words, month names, weekdays, etc. As part of linguistic features for Hindi, the system uses only the lists of first names, middle names, last names, function words, month names and weekdays along with the list of words that helps to recognize measurements. In addition to the other features, part of speech (POS) information of the word has been also considered for Bengali and Hindi. No linguistic features have been considered for Telugu, Oriya and Urdu. It has been observed from the evaluation results that the use of linguistic features improves the performance of the system. The system has been trained with 122,467 Bengali, 502,974 Hindi, 64,026 Telugu, 93,173 Oriya and 35,447 Urdu tokens. The system has demonstrated the highest overall average Recall, Precision, and F-Score values of 88.01%, 82.63%, and 85.22%, respectively, for Bengali with the 10-fold cross validation test. Experimental results of the 10-fold cross validation tests on the Hindi, Telugu, Oriya, and Urdu data have shown the overall average F-Score values of 82.66%, 70.11%, 70.13%, and 69.3%, respectively.

This paper presents a novel framework of speaker identification based on Chinese vowel mapping theory. The base of this framework is the mapping from Chinese multi-phthong to monophthong phonemes. According to the contrast of spectrum, features, monophthong phoneme glide statistical distribution and the performance of vowel classification, we confirmed that Chinese vowels could be decomposed into several monophthong phonemes based on the short time characteristics. Then we developed a new mapping table from multi-phthong to monophthong phoneme to assist the latter research of a great deal of experiment and theory analysis. The novel framework added a special model to implement the decomposition and organized several monophthong classifiers to replace the traditional classification module, which can avoid the disturbance of semantic information and achieve higher performance. In this new framework, it adopts short time frame as the basic identify unit, which makes it more compatible to real time system. The sufficient theory analysis and experimental results showed that the presented model and algorithms based on novel framework have achieved higher accuracy, speed and enhanced the robustness in different conditions compared with many traditional methods. Especially, we succeed in separating personal identification information from semantic information based on classifying the Chinese vowel, which will be a new way to transform the text-independent system into text-dependent speaker recognition system.

The modification of a standard character according to the features of an individual's handwriting endows the character with handwritten traits, a process called font personalization. In this paper, a novel approach is proposed to transform a full set of standard Chinese vectorized font, according to a writer's handwritten characteristics, into a personalized font possessing the writer's discernible features. Once installed in a computer, the personalized font set obtained can efficiently replace existing standard fonts to exhibit unique handwritten features.

The Arabic language is a highly derivational and inflexional language in which morphology plays a significant role. However, a large number of the derivations obey a set of pre-defined rules and when applied, they do not only produce a set of related words but also associate contextual and semantic knowledge to these words. In this paper, we describe the Meta-Ontology DEAR-ONTO, A DErivational ARabic Ontology used to model the Arabic Language. The Meta-Ontology uses verbs as roots and identifies the various classes formed by the derived words. Some of the possible applications of the DEAR-Ontology are discussed.