S
Shafiq Joty
Researcher at Salesforce.com
Publications - 273
Citations - 6451
Shafiq Joty is an academic researcher from Salesforce.com. The author has contributed to research in topics: Computer science & Machine translation. The author has an hindex of 36, co-authored 219 publications receiving 4314 citations. Previous affiliations of Shafiq Joty include University of British Columbia & Nanyang Technological University.
Papers
More filters
Proceedings ArticleDOI
Look, Imagine and Match: Improving Textual-Visual Cross-Modal Retrieval with Generative Models
TL;DR: This work proposes to incorporate generative processes into the cross-modal feature embedding, through which it is able to learn not only the global abstract features but also the local grounded features of image-text pairs.
Proceedings ArticleDOI
Fine-grained Opinion Mining with Recurrent Neural Networks and Word Embeddings
TL;DR: This work proposes a general class of discriminative models based on recurrent neural networks and word embeddings that can be successfully applied to fine-grained opinion mining tasks without any taskspecific feature engineering effort.
Proceedings ArticleDOI
Distributed representations of tuples for entity resolution
TL;DR: This work proposes a locality sensitive hashing (LSH) based blocking approach that takes all attributes of a tuple into consideration and produces much smaller blocks, compared with traditional methods that consider only a few attributes.
Journal ArticleDOI
Conversational Agents in Health Care: Scoping Review and Conceptual Analysis.
Lorainne Tudor Car,Lorainne Tudor Car,Dhakshenya Ardhithy Dhinagaran,Bhone Myint Kyaw,Tobias Kowatsch,Tobias Kowatsch,Shafiq Joty,Yin-Leng Theng,Rifat Atun +8 more
TL;DR: There is an urgent need for a robust evaluation of diverse health care conversational agents’ formats, focusing on their acceptability, safety, and effectiveness.
Journal ArticleDOI
Codra: A novel discriminative framework for rhetorical analysis
TL;DR: It is demonstrated that CODRA significantly outperforms the state-of-the-art, often by a wide margin, and that a reranking of the k-best parse hypotheses generated by COD RA can potentially improve the accuracy even further.