P
Partha Pakray
Researcher at National Institute of Technology, Silchar
Publications - 55
Citations - 321
Partha Pakray is an academic researcher from National Institute of Technology, Silchar. The author has contributed to research in topics: Machine translation & Computer science. The author has an hindex of 6, co-authored 54 publications receiving 150 citations. Previous affiliations of Partha Pakray include Techno India.
Papers
More filters
Journal ArticleDOI
English–Mizo Machine Translation using neural and statistical approaches
TL;DR: Translations predicted by the two approaches have been comparatively and adequately analyzed on a number of grounds to infer their strengths and weaknesses, particularly in low-resource scenarios.
Proceedings ArticleDOI
English to Hindi Multi-modal Neural Machine Translation and Hindi Image Captioning
TL;DR: The official results evaluated at WAT2019 translation task shows that the multi-modal NMT system achieved Bilin-gual Evaluation Understudy (BLEU) score20, Rank-based Intuitive Bilingual Eval-uation Score (RIBES) 0.642838, Adequacy-Fluency Metrics (AMFM) score 0.668260 forchallenge test data and BLEU score 40.760080 for challenge test data.
Book ChapterDOI
Neural Machine Translation for Low Resource Assamese–English
TL;DR: In this article, the authors contribute an Assamese-English parallel corpus and build two NMT systems, sequence-to-sequence recurrent neural network (RNN) with attention mechanism (NMT-1) and a transformer model having self-attention mechanism (nMT-2).
Proceedings ArticleDOI
Neural Machine Translation: Hindi-Nepali
TL;DR: Current work relies on the Neural Machine Translation with attention mechanism for the similar language translation of WMT19 shared task in the context of Hindi-Nepali pair, which shows that the NMT system obtained Bilingual Evaluation Understudy (BLEU) score 24.6 for primary configuration in Nepali to Hindi translation.
Proceedings ArticleDOI
LSTM Neural Network Based Math Information Retrieval
TL;DR: Role of Long Sort-Term Memory (LSTM) neural network in Math Information Retrieval (MIR) is ascertains and competence of the implemented MIR system in retrieving relevant documents corresponding to a mathematical user query is substantiated.