Search

Your search keyword '"English–Tamil"' showing total 3 results
Start Over Descriptor "English–Tamil"
3 results on '"English–Tamil"'

1. Intrinsic Evaluation for English–Tamil Bilingual Word Embeddings

Author

Sanjanasri, J. P., Menon, Vijay Krishna, Rajendran, S., Soman, K. P., Anand Kumar, M., Kacprzyk, Janusz, Series Editor, Pal, Nikhil R., Advisory Editor, Bello Perez, Rafael, Advisory Editor, Corchado, Emilio S., Advisory Editor, Hagras, Hani, Advisory Editor, Kóczy, László T., Advisory Editor, Kreinovich, Vladik, Advisory Editor, Lin, Chin-Teng, Advisory Editor, Lu, Jie, Advisory Editor, Melin, Patricia, Advisory Editor, Nedjah, Nadia, Advisory Editor, Nguyen, Ngoc Thanh, Advisory Editor, Wang, Jun, Advisory Editor, Thampi, Sabu M., editor, Trajkovic, Ljiljana, editor, Mitra, Sushmita, editor, Nagabhushan, P., editor, Mukhopadhyay, Jayanta, editor, Corchado, Juan M., editor, Berretti, Stefano, editor, and Mishra, Deepak, editor

Published
2020
Full Text
View/download PDF

2. Generation of Cross-Lingual Word Vectors for Low-Resourced Languages Using Deep Learning and Topological Metrics in a Data-Efficient Way

Author

Soman Kp, Vijay Krishna Menon, Sanjanasri Jp, Agnieszka Wolk, and Rajendran S

Subjects
Word embedding, TK7800-8360, Computer Networks and Communications, Computer science, Semantic interpretation, bilingual embedding, 02 engineering and technology, semantic interpretation, transfer learning, computer.software_genre, Semantics, ontology engineering, topological measures, cross-lingual embedding, 0202 electrical engineering, electronic engineering, information engineering, Word2vec, Electrical and Electronic Engineering, business.industry, Bilingual dictionary, Deep learning, English–Tamil, 020206 networking & telecommunications, Automatic summarization, language.human_language, low resourced languages, Hardware and Architecture, Control and Systems Engineering, Tamil, Signal Processing, language, 020201 artificial intelligence & image processing, Artificial intelligence, Electronics, business, computer, Natural language processing
Abstract

Linguists have been focused on a qualitative comparison of the semantics from different languages. Evaluation of the semantic interpretation among disparate language pairs like English and Tamil is an even more formidable task than for Slavic languages. The concept of word embedding in Natural Language Processing (NLP) has enabled a felicitous opportunity to quantify linguistic semantics. Multi-lingual tasks can be performed by projecting the word embeddings of one language onto the semantic space of the other. This research presents a suite of data-efficient deep learning approaches to deduce the transfer function from the embedding space of English to that of Tamil, deploying three popular embedding algorithms: Word2Vec, GloVe and FastText. A novel evaluation paradigm was devised for the generation of embeddings to assess their effectiveness, using the original embeddings as ground truths. Transferability across other target languages of the proposed model was assessed via pre-trained Word2Vec embeddings from Hindi and Chinese languages. We empirically prove that with a bilingual dictionary of a thousand words and a corresponding small monolingual target (Tamil) corpus, useful embeddings can be generated by transfer learning from a well-trained source (English) embedding. Furthermore, we demonstrate the usability of generated target embeddings in a few NLP use-case tasks, such as text summarization, part-of-speech (POS) tagging, and bilingual dictionary induction (BDI), bearing in mind that those are not the only possible applications.

Published
2021

3. Generation of Cross-Lingual Word Vectors for Low-Resourced Languages Using Deep Learning and Topological Metrics in a Data-Efficient Way.

Author

JP, Sanjanasri, Menon, Vijay Krishna, KP, Soman, S, Rajendran, and Wolk, Agnieszka

Subjects
NATURAL language processing, DEEP learning, CHINESE language, SLAVIC languages, HINDI language, TRANSFER functions
Abstract

Linguists have been focused on a qualitative comparison of the semantics from different languages. Evaluation of the semantic interpretation among disparate language pairs like English and Tamil is an even more formidable task than for Slavic languages. The concept of word embedding in Natural Language Processing (NLP) has enabled a felicitous opportunity to quantify linguistic semantics. Multi-lingual tasks can be performed by projecting the word embeddings of one language onto the semantic space of the other. This research presents a suite of data-efficient deep learning approaches to deduce the transfer function from the embedding space of English to that of Tamil, deploying three popular embedding algorithms: Word2Vec, GloVe and FastText. A novel evaluation paradigm was devised for the generation of embeddings to assess their effectiveness, using the original embeddings as ground truths. Transferability across other target languages of the proposed model was assessed via pre-trained Word2Vec embeddings from Hindi and Chinese languages. We empirically prove that with a bilingual dictionary of a thousand words and a corresponding small monolingual target (Tamil) corpus, useful embeddings can be generated by transfer learning from a well-trained source (English) embedding. Furthermore, we demonstrate the usability of generated target embeddings in a few NLP use-case tasks, such as text summarization, part-of-speech (POS) tagging, and bilingual dictionary induction (BDI), bearing in mind that those are not the only possible applications. [ABSTRACT FROM AUTHOR]

Published
2021
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results