Leveraging Pretrained Image Classifiers for Language-Based Segmentation

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.

Object Segmentation +1

Learning to Write with Cooperative Discriminators

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.

Two-Stage Synthesis Networks for Transfer Learning in Machine Comprehension

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).

Reading Comprehension Transfer Learning +1

Character-Level Question Answering with Attention

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.

Data Augmentation Question Answering