• Publications
  • Influence
DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation
TLDR
We present a large, tunable neural conversational response generation model, DIALOGPT (dialogue generative pre-trained transformer). Expand
Patient Knowledge Distillation for BERT Model Compression
TLDR
We propose a Patient Knowledge Distillation approach to compress an original large model (teacher) into an equally-effective lightweight shallow network (student). Expand
UNITER: Learning UNiversal Image-TExt Representations
TLDR
We introduce UNiversal Image-TExt Representation, learned through large-scale pre-training over four image-text datasets (COCO, Visual Genome, Conceptual Captions and SBU Captions), which can power heterogeneous downstream V+L tasks with joint multimodal embeddings. Expand
UNITER: UNiversal Image-TExt Representation Learning
TLDR
We introduce UNiversal Image-TExt Representation, learned through large-scale pre-training over four image-text datasets, which can power heterogeneous downstream V+L tasks with joint multimodal embeddings. Expand
ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension
TLDR
We present a large-scale dataset, ReCoRD, for machine reading comprehension requiring commonsense reasoning. Expand
FreeLB: Enhanced Adversarial Training for Natural Language Understanding
TLDR
We propose a novel adversarial training algorithm, FreeLB, that promotes higher invariance in the embedding space, by adding adversarial perturbations to word embeddings and minimizing the resultant adversarial risk inside different regions around input samples. Expand
Tactical Rewind: Self-Correction via Backtracking in Vision-And-Language Navigation
TLDR
We present the Frontier Aware Search with backTracking (FAST) Navigator, a general framework for action decoding, that achieves state-of-the-art results on the 2018 Room-to-Room (R2R) Vision-and-Language navigation challenge. Expand
FreeLB: Enhanced Adversarial Training for Language Understanding
TLDR
We propose a novel adversarial training algorithm - FreeLB, that promotes higher robustness and invariance in the embedding space, by adding adversarial perturbations to word embeddings and minimizing the resultant adversarial risk inside different regions around input samples. Expand
Relation-Aware Graph Attention Network for Visual Question Answering
TLDR
We propose a Relation-aware Graph Attention Network (ReGAT), which encodes each image into a graph and models multi-type inter-object relations via a graph attention mechanism, to learn question-adaptive relation representations. Expand
Integrating planning for task-completion dialogue policy learning
TLDR
This paper addresses these challenges by integrating planning into the dialogue policy learning based on Dyna-Q framework, and provides a more sample-efficient approach to learn the dialogue polices. Expand
...
1
2
3
4
5
...