P
Pushpak Bhattacharyya
Researcher at Indian Institute of Technology Patna
Publications - 576
Citations - 8724
Pushpak Bhattacharyya is an academic researcher from Indian Institute of Technology Patna. The author has contributed to research in topics: Machine translation & WordNet. The author has an hindex of 38, co-authored 576 publications receiving 6465 citations. Previous affiliations of Pushpak Bhattacharyya include Xerox & IBM.
Papers
More filters
Posted Content
Indowordnets help in Indian Language Machine Translation
TL;DR: In this article, a comparative study of 440 phrase-based statistical trained models for 110 language pairs across 11 Indian languages is presented, where the training corpus with Indowordnet synset word entries of lexical database and further trained 110 models on top of the baseline system.
Proceedings ArticleDOI
Keep Your Dimensions on a Leash: True Cognate Detection using Siamese Deep Neural Networks
TL;DR: A Siamese Feed-forward neural network with word-embeddings is used to detect Cognate words across languages which exhibit partial or full lexical similarity and mean the same (e.g., hund-hound in German-English).
Proceedings ArticleDOI
Semantic analysis of 'to'
TL;DR: This paper describes the analysis of the sentences involving `to', which poses problems at lexical, syntactic and semantic level, as it needs to resolve whether the phrase which is fronted by `to' is a prepositional phrase (PP) or an infinitival clause which is a kind of inflectional phrase (IP).
Proceedings Article
PaCMan : Parallel Corpus Management Workbench
TL;DR: A novel tool that provides aides like references to various dictionary sources such as Wordnets, Shabdkosh, Wikitionary etc, providing a valuable source of word / phrase alignments and can lead to its gamification in the future.
Posted Content
COVIDRead: A Large-scale Question Answering Dataset on COVID-19.
TL;DR: The COVIDRead dataset as discussed by the authors consists of Context-Answer-Question triples, which are manually checked by hu-mans annotators in an automated way, and the questions from the context are constructed by the annotators.