Search Results: 1 - 10 of 100 matches for " "
All listed articles are free for downloading (OA Articles)
Page 1 /100
Display every page Item
Morphological Cross Reference method for English to Telugu Transliteration  [PDF]
A. P. Siva kumar,P. Premchand,A. Govardhan
International Journal of Artificial Intelligence & Applications , 2011,
Abstract: Machine Transliteration is a sub field of Computational linguistics for automatically converting letters in one language to another language, which deals with Grapheme or Phoneme based transliteration approaches. Several methods for Machine Transliteration have been proposed till date based on nature of languages considered, but those methods are having less precision for English to Telugu transliteration when both pronunciation and spelling of the word is considered. Morphological cross reference approachprovides user friendly environment for transliteration of English to Telugu text, where both the pronunciation and the spelling of the word is taken into consideration to improve the precision of transliteration system. In addition to alphabet by alphabet transliteration, this paper also deals with whole document transliteration. Our system achieved an correct transliteration with an accuracy of '78%' of Transliteration for Vocabulary words.
Unlimited Vocabulary Grapheme to Phoneme Conversion for Korean TTS  [PDF]
Byeongchang Kim,WonIl Lee,Geunbae Lee,Jong-Hyeok Lee
Computer Science , 1998,
Abstract: This paper describes a grapheme-to-phoneme conversion method using phoneme connectivity and CCV conversion rules. The method consists of mainly four modules including morpheme normalization, phrase-break detection, morpheme to phoneme conversion and phoneme connectivity check. The morpheme normalization is to replace non-Korean symbols into standard Korean graphemes. The phrase-break detector assigns phrase breaks using part-of-speech (POS) information. In the morpheme-to-phoneme conversion module, each morpheme in the phrase is converted into phonetic patterns by looking up the morpheme phonetic pattern dictionary which contains candidate phonological changes in boundaries of the morphemes. Graphemes within a morpheme are grouped into CCV patterns and converted into phonemes by the CCV conversion rules. The phoneme connectivity table supports grammaticality checking of the adjacent two phonetic morphemes. In the experiments with a corpus of 4,973 sentences, we achieved 99.9% of the grapheme-to-phoneme conversion performance and 97.5% of the sentence conversion performance. The full Korean TTS system is now being implemented using this conversion method.
A Comparison of Different Machine Transliteration Models  [PDF]
K. Choi,H. Isahara,J. Oh
Computer Science , 2011, DOI: 10.1613/jair.1999
Abstract: Machine transliteration is a method for automatically converting words in one language into phonetically equivalent ones in another language. Machine transliteration plays an important role in natural language applications such as information retrieval and machine translation, especially for handling proper nouns and technical terms. Four machine transliteration models -- grapheme-based transliteration model, phoneme-based transliteration model, hybrid transliteration model, and correspondence-based transliteration model -- have been proposed by several researchers. To date, however, there has been little research on a framework in which multiple transliteration models can operate simultaneously. Furthermore, there has been no comparison of the four models within the same framework and using the same data. We addressed these problems by 1) modeling the four models within the same framework, 2) comparing them under the same conditions, and 3) developing a way to improve machine transliteration through this comparison. Our comparison showed that the hybrid and correspondence-based models were the most effective and that the four models can be used in a complementary manner to improve machine transliteration performance.
A Finite State and Data-Oriented Method for Grapheme to Phoneme Conversion  [PDF]
Gosse Bouma
Computer Science , 2000,
Abstract: A finite-state method, based on leftmost longest-match replacement, is presented for segmenting words into graphemes, and for converting graphemes into phonemes. A small set of hand-crafted conversion rules for Dutch achieves a phoneme accuracy of over 93%. The accuracy of the system is further improved by using transformation-based learning. The phoneme accuracy of the best system (using a large set of rule templates and a `lazy' variant of Brill's algoritm), trained on only 40K words, reaches 99% accuracy.
Sequence-to-Sequence Neural Net Models for Grapheme-to-Phoneme Conversion  [PDF]
Kaisheng Yao,Geoffrey Zweig
Computer Science , 2015,
Abstract: Sequence-to-sequence translation methods based on generation with a side-conditioned language model have recently shown promising results in several tasks. In machine translation, models conditioned on source side words have been used to produce target-language text, and in image captioning, models conditioned images have been used to generate caption text. Past work with this approach has focused on large vocabulary tasks, and measured quality in terms of BLEU. In this paper, we explore the applicability of such models to the qualitatively different grapheme-to-phoneme task. Here, the input and output side vocabularies are small, plain n-gram models do well, and credit is only given when the output is exactly correct. We find that the simple side-conditioned generation approach is able to rival the state-of-the-art, and we are able to significantly advance the stat-of-the-art with bi-directional long short-term memory (LSTM) neural networks that use the same alignment information that is used in conventional approaches.
Treinamento de habilidades fonológicas e correspondência grafema-fonema em crian as de risco para dislexia Phonological skills and grapheme-phoneme training correspondence in children under dyslexia risk
Maryse Tomoko Matsuzawa Fukuda,Simone Aparecida Capellini
Revista CEFAC , 2011,
Abstract: OBJETIVO: verificar a eficácia do programa de treinamento fonológico e correspondência grafema-fonema em crian as de risco para dislexia da 1a série. MéTODOS: participaram deste estudo 30 crian as de 1a série de ensino público, de ambos os gêneros, na faixa etária de 6 a 7 anos de idade. Neste estudo foi realizada a adapta o brasileira da pesquisa sobre treinamento de habilidades fonológicas e correspondência grafema-fonema composta de pré-testagem, interven o e pós-testagem. Em situa o de pré e pós-testagem, todas as crian as foram submetidas à aplica o do teste para identifica o precoce dos problemas de leitura e aquelas que apresentaram desempenho inferior a 51% das provas do teste foram divididas em Grupo I (GI): composto por 15 crian as submetidas ao programa de treinamento; e em Grupo II (GII): composto por 15 crian as n o submetidas ao programa de treinamento. RESULTADOS: os resultados desse estudo revelaram diferen as estatisticamente significantes, evidenciando que das 15 crian as submetidas ao programa, apenas uma n o respondeu à interven o proposta, sendo submetida, portanto, à avalia o interdisciplinar e confirmado o diagnóstico de dislexia. CONCLUS O: a realiza o do programa de treinamento das habilidades fonológicas e correspondência grafema-fonema foi eficaz para a identifica o das crian as com sinais de dislexia, comprovado pela melhora das habilidades fonológicas e leitura em situa o de pós-testagem em rela o à pré-testagem, evidenciando que quando é fornecida a instru o formal do princípio alfabético associado ao principio de convers o letra-som da Língua Portuguesa, as crian as que n o apresentam dislexia deixam de apresentar suas manifesta es com resposta à instru o formal do princípio alfabético. PURPOSE: to check the efficacy of the phonological training and grapheme-phoneme correspondence program in first-grade children under dyslexia risk. METHODS: thirty municipal public study students of both genders from 1st grade took part, ranging from 6 to 7 year old. In this study we used the Brazilian adaptation of the research on phonological abilities training and grapheme-phoneme correspondence composed of pre-testing, training, and post-testing. In the pre and post-testing situation, all children were submitted to the test for early identification of reading problems and those who presented less than 51% of the tasks of the test were divided into Group I (GI): consisted of 15 children who were submitted to the training program; and Group II (GII): consisted of 15 children who were not submitted to the training program. R
Machine Transliteration  [PDF]
Kevin Knight,Jonathan Graehl
Computer Science , 1997,
Abstract: It is challenging to translate names and technical terms across languages with different alphabets and sound inventories. These items are commonly transliterated, i.e., replaced with approximate phonetic equivalents. For example, "computer" in English comes out as "konpyuutaa" in Japanese. Translating such items from Japanese back to English is even more challenging, and of practical interest, as transliterated items make up the bulk of text phrases not found in bilingual dictionaries. We describe and evaluate a method for performing backwards transliterations by machine. This method uses a generative model, incorporating several distinct stages in the transliteration process.
Hybrid Approach to English-Hindi Name Entity Transliteration  [PDF]
Shruti Mathur,Varun Prakash Saxena
Computer Science , 2014,
Abstract: Machine translation (MT) research in Indian languages is still in its infancy. Not much work has been done in proper transliteration of name entities in this domain. In this paper we address this issue. We have used English-Hindi language pair for our experiments and have used a hybrid approach. At first we have processed English words using a rule based approach which extracts individual phonemes from the words and then we have applied statistical approach which converts the English into its equivalent Hindi phoneme and in turn the corresponding Hindi word. Through this approach we have attained 83.40% accuracy.
Grapheme-to-Phoneme Conversion using Multiple Unbounded Overlapping Chunks  [PDF]
Francois Yvon
Computer Science , 1996,
Abstract: We present in this paper an original extension of two data-driven algorithms for the transcription of a sequence of graphemes into the corresponding sequence of phonemes. In particular, our approach generalizes the algorithm originally proposed by Dedina and Nusbaum (D&N) (1991), which had originally been promoted as a model of the human ability to pronounce unknown words by analogy to familiar lexical items. We will show that DN's algorithm performs comparatively poorly when evaluated on a realistic test set, and that our extension allows us to improve substantially the performance of the analogy-based model. We will also suggest that both algorithms can be reformulated in a much more general framework, which allows us to anticipate other useful extensions. However, considering the inability to define in these models important notions like lexical neighborhood, we conclude that both approaches fail to offer a proper model of the analogical processes involved in reading aloud.
Particle Swarm Optimization in Transliteration
Dr. Pothula Sujatha
International Journal of Computer Trends and Technology , 2012,
Abstract: Transliteration is the process of transforming a word written in a source language into a word in a target language without the aid of a resource like a bilingual dictionary. This process generates the target language word for a given source language word, but need to find the similarity between source and target words. That is, in order to check how far the generated target word is right equivalent an edit distance calculation is needed between source and target languages words. Presently there was no automated process for finding edit cost between source and target languages words. This work proposes a new Particle Swarm Optimization (PSO) algorithm which is used in the transliteration algorithm process for finding optimal cost between source and target words.
Page 1 /100
Display every page Item

Copyright © 2008-2017 Open Access Library. All rights reserved.