The work aims at alleviating the loss of translation quality arising due to the frequent occurrence of Out-of-Vocabulary (OOV) words during machine translation of low-resource languages (LRLs). We propose a novel word-to-character embedding mapping algorithm and apply these upon three variants of attention-based seq2seq models to perform transduction of such words from Hindi to Bhojpuri…
MTDMA: Multi-task Deep Morphological Analyzer
The project aims at predicting: Parts-of-speech (POS), Gender (G), Number (N), Person (P), Case (C), Tense-aspect-mood (TAM) marker as well as the Lemma (L) or roots of words occurring in Hindustani texts (viz. Hindi and Urdu), by sharing the knowledge learned while capturing the representation of each of these in a multi-task learning…
Bringing Cartoons to Life: Towards Improved Cartoon Face Detection and Recognition Systems
Given the recent deep learning advancements in face detection and recognition techniques for human faces, this paper answers the question “how well would they work for cartoons’?” – a domain that remains largely unexplored until recently, mainly due to the unavailability of large scale datasets and the failure of traditional methods on these….