Pushpak Bhattacharyya

TL;DR: A compendium of 110 Statistical Machine Translation systems built from parallel corpora of 11 Indian languages belonging to both Indo-Aryan and Dravidian families is presented and the relationship between translation accuracy and the language families involved is analyzed.

TL;DR: Various deep learning models for detecting fake news and classifying them into the pre-defined fine-grained categories are developed based on Convolutional Neural Network and Bi-directional Long Short Term Memory networks.

TL;DR: This work describes a transliteration model based on FST and UIT, and evaluates it on Hindi and Urdu corpora, and introduces UIT (universal intermediate transcription) for the same pair on the basis of their common phonetic repository.

TL;DR: This paper proposes an unsupervised method for MFS detection from the untagged corpora, which exploits word embeddings and obtains the predominant sense with the highest similarity.

TL;DR: A universal Parts-of-Speech (POS) tagset framework covering most of the Indian languages following the hierarchical and decomposable tagset schema is presented, which enables the framework to be flexible enough to capture rich features of a language/ language family, even while capturing the shared linguistic structures in a methodical way.