
-
VinVL: Making Visual Representations Matter in Vision-Language Models
This paper presents a detailed study of improving visual representations...
read it
-
Self-supervised Pre-training with Hard Examples Improves Visual Representations
Self-supervised pre-training (SSP) employs random image transformations ...
read it
-
MiniVLM: A Smaller and Faster Vision-Language Model
Recent vision-language (VL) studies have shown remarkable progress by le...
read it
-
Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks
Large-scale pre-training methods of learning cross-modal representations...
read it
-
Optimus: Organizing Sentences via Pre-trained Modeling of a Latent Space
When trained effectively, the Variational Autoencoder (VAE) can be both ...
read it
-
Multi-View Learning for Vision-and-Language Navigation
Learning to navigate in a visual environment following natural language ...
read it
-
Few-shot Natural Language Generation for Task-Oriented Dialog
As a crucial component in task-oriented dialog systems, the Natural Lang...
read it
-
Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training
Learning to navigate in a visual environment following natural-language ...
read it
-
Robust Navigation with Language Pretraining and Stochastic Sampling
Core to the vision-and-language navigation (VLN) challenge is building r...
read it
-
Budgeted Policy Learning for Task-Oriented Dialogue Systems
This paper presents a new approach that extends Deep Dyna-Q (DDQ) by inc...
read it
-
ConvLab: Multi-Domain End-to-End Dialog System Platform
We present ConvLab, an open-source multi-domain end-to-end dialog system...
read it
-
Tactical Rewind: Self-Correction via Backtracking in Vision-and-Language Navigation
We present FAST NAVIGATOR, a general framework for action decoding, whic...
read it
-
Switch-based Active Deep Dyna-Q: Efficient Adaptive Planning for Task-Completion Dialogue Policy Learning
Training task-completion dialogue agents with reinforcement learning usu...
read it
-
A bird's-eye view on coherence, and a worm's-eye view on cohesion
Generating coherent and cohesive long-form texts is a challenging proble...
read it
-
Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization
Responses generated by neural conversational models tend to lack informa...
read it
-
Discriminative Deep Dyna-Q: Robust Planning for Dialogue Policy Learning
This paper presents a Discriminative Deep Dyna-Q (D3Q) approach to impro...
read it
-
Interactive Semantic Parsing for If-Then Recipes via Hierarchical Reinforcement Learning
Given a text description, most existing semantic parsers synthesize a pr...
read it
-
Microsoft Dialogue Challenge: Building End-to-End Task-Completion Dialogue Systems
This proposal introduces a Dialogue Challenge for building end-to-end ta...
read it
-
Subgoal Discovery for Hierarchical Dialogue Policy Learning
Developing conversational agents to engage in complex dialogues is chall...
read it
-
Integrating planning for task-completion dialogue policy learning
Training a task-completion dialogue agent with real users via reinforcem...
read it
-
BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems
We present a new algorithm that significantly improves the efficiency of...
read it
-
Adversarial Advantage Actor-Critic Model for Task-Completion Dialogue Policy Learning
This paper presents a new method --- adversarial advantage actor-critic ...
read it
-
Composite Task-Completion Dialogue Policy Learning via Hierarchical Deep Reinforcement Learning
Building a dialogue agent to fulfill complex tasks, such as travel plann...
read it
-
Investigation of Language Understanding Impact for Reinforcement Learning Based Dialogue Systems
Language understanding is a key component in a spoken dialogue system. I...
read it
-
End-to-End Task-Completion Neural Dialogue Systems
One of the major drawbacks of modularized task-completion dialogue syste...
read it
-
A User Simulator for Task-Completion Dialogues
Despite widespread interests in reinforcement-learning for task-oriented...
read it
-
End-to-End Joint Learning of Natural Language Understanding and Dialogue Manager
Natural language understanding and dialogue policy learning are both ess...
read it
-
Towards End-to-End Reinforcement Learning of Dialogue Agents for Information Access
This paper proposes KB-InfoBot -- a multi-turn dialogue agent which help...
read it
-
Recurrent Reinforcement Learning: A Hybrid Approach
Successful applications of reinforcement learning in real-world problems...
read it