Pushpak Bhattacharyya

TL;DR: An unsupervised approach for substring-based transliteration which incorporates two new sources of knowledge in the learning process: context by learning substring mappings, as opposed to single character mappings and phonetic features which capture cross-lingual character similarity via prior distributions.

TL;DR: Insight is provided into the de-identification task, its major challenges, techniques to address challenges, detailed analysis of the results and direction of future improvement, and a supervised machine learning technique for solving the problem of patient data deidentification.

TL;DR: This survey surveys various techniques for jointly extracting entities and relations, and categorizes techniques based on the approach they adopt for joint extraction, i.e. whether they employ joint inference or joint modelling or both.

TL;DR: A novel retrofitting model that can leverage relational knowledge available in a knowledge resource to improve word embeddings is presented and large gains in performance over original distributional models as well as other retrofitting approaches on word similarity task and significant overall improvement on lexical entailment detection task are observed.

TL;DR: Evaluation and analysis suggest that joint-learning of the related tasks in a multi-task framework can outperform each of the individual tasks in the single-task frameworks.