S
Sonal Gupta
Researcher at Facebook
Publications - 78
Citations - 2293
Sonal Gupta is an academic researcher from Facebook. The author has contributed to research in topics: Computer science & Parsing. The author has an hindex of 21, co-authored 58 publications receiving 1442 citations. Previous affiliations of Sonal Gupta include Department of Biotechnology & University of Texas at Austin.
Papers
More filters
Proceedings ArticleDOI
Cross-lingual Transfer Learning for Multilingual Task Oriented Dialog
TL;DR: This paper presents a new data set of 57k annotated utterances in English, Spanish, Spanish and Thai and uses this data set to evaluate three different cross-lingual transfer methods, finding that given several hundred training examples in the the target language, the latter two methods outperform translating the training data.
Proceedings ArticleDOI
Make-A-Video: Text-to-Video Generation without Text-Video Data
Uriel Singer,Adam Polyak,Thomas Hayes,Xiaoyue Yin,Jie An,Songyang Zhang,Qiyuan Hu,Harry Yang,Oron Ashual,Oran Gafni,Devi Parikh,Sonal Gupta,Yaniv Taigman +12 more
TL;DR: Make-A-Video sets the new state-of-the-art in text-to-video generation, as determined by both qualitative and quantitative measures.
Proceedings ArticleDOI
Semantic Parsing for Task Oriented Dialog using Hierarchical Representations
TL;DR: This work proposes a hierarchical annotation scheme for semantic parsing that allows the representation of compositional queries, and can be efficiently and accurately parsed by standard constituency parsing models.
Proceedings ArticleDOI
Improved Pattern Learning for Bootstrapped Entity Extraction
TL;DR: This paper uses various unsupervised features based on contrasting domain-specific and general text, and exploiting distributional similarity and edit distances to learned entities to improve pattern scoring.
Proceedings Article
Analyzing the Dynamics of Research by Extracting Key Aspects of Scientific Papers
TL;DR: A method for characterizing a research work in terms of its focus, domain of application, and techniques used is presented and it is shown how tracing these aspects over time provides a novel measure of the influence of research communities on each other.