no code implementations • 3 Nov 2019 • David Golub, Ahmed El-Kishky, Roberto Martín-Martín
Current semantic segmentation models cannot easily generalize to new object classes unseen during train time: they require additional annotated images and retraining.
2 code implementations • ACL 2018 • Ari Holtzman, Jan Buys, Maxwell Forbes, Antoine Bosselut, David Golub, Yejin Choi
Recurrent Neural Networks (RNNs) are powerful autoregressive sequence models, but when used to generate natural language their output tends to be overly generic, repetitive, and self-contradictory.
2 code implementations • EMNLP 2017 • David Golub, Po-Sen Huang, Xiaodong He, Li Deng
We develop a technique for transfer learning in machine comprehension (MC) using a novel two-stage synthesis network (SynNet).
1 code implementation • EMNLP 2016 • David Golub, Xiaodong He
We show that a character-level encoder-decoder framework can be successfully applied to question answering with a structured knowledge base.