Papers by Xiujun Li
Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learning (P18-1)
Copied to clipboard
| Challenge: | Training a task-completion dialogue agent via reinforcement learning (RL) is costly because it requires many interactions with real users. |
| Approach: | They propose a framework that integrates planning for task-completion dialogue policy learning into a dialogue agent using a world model to mimic real user response and generate simulated experience. |
| Outcome: | The proposed framework integrates planning for task-completion dialogue policy learning with real user interaction and simulated user behavior. |
Optimus: Organizing Sentences via Pre-trained Modeling of a Latent Space (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing models for language understanding and understanding can be trained to provide contextualized representations of words based on text data. |
| Approach: | They propose a large-scale language VAE model Optimus that is pre-trained on large text corpus and fine-tuned for various language generation and understanding tasks. |
| Outcome: | The proposed model achieves new state-of-the-art on VAE language modeling benchmarks. |
Sentiment Forecasting in Dialog (2020.coling-main)
Copied to clipboard
| Challenge: | Existing studies on sentiment classification focus on determining polarity of existing utterances. |
| Approach: | They propose a Neural Sentiment Forecasting task which simulates the next utterance based on context and a sequence influence model to learn both pair-wise and seq-wise influence. |
| Outcome: | The proposed model outperforms existing models over several strong baselines. |
Few-shot Natural Language Generation for Task-Oriented Dialog (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for NLG depend on heavily annotated data, which is infeasible for new domains. |
| Approach: | They propose a system that converts a dialog act into a response in natural language . they propose 'nuclear language generation' to simulate a few-shot learning setting . |
| Outcome: | The proposed model outperforms existing methods on a large set of annotated datasets. |
Discriminative Deep Dyna-Q: Robust Planning for Dialogue Policy Learning (D18-1)
Copied to clipboard
| Challenge: | Existing approaches to improve the effectiveness and robustness of Deep Dyna-Q (DDQ) are based on a discriminator to control the quality of simulated experiences and to improve learning. |
| Approach: | They propose to use an RNN-based discriminator to control the quality of simulated experience to improve the effectiveness and robustness of Deep Dyna-Q. |
| Outcome: | The proposed framework outperforms DDQ by controlling the quality of simulated experience used for planning. |
Subgoal Discovery for Hierarchical Dialogue Policy Learning (D18-1)
Copied to clipboard
| Challenge: | Existing methods to develop dialogue agents for complex tasks require sparse reward signals. |
| Approach: | They propose a divide-and-conquer approach that exploits the hidden structure of a task . they use subgoals to divide a goal-oriented task into simpler subgoal sets . |
| Outcome: | The proposed approach performs competitively against state-of-the-art methods that require human-defined subgoals. |
Budgeted Policy Learning for Task-Oriented Dialogue Systems (P19-1)
Copied to clipboard
| Challenge: | Existing approaches to integrating reinforcement learning into task-oriented dialogue systems require a fixed, small amount of user interactions to learn. |
| Approach: | They propose a budget-conscious scheduling approach that optimizes a fixed, small amount of user interactions for dialogue agent learning. |
| Outcome: | The proposed approach improves on a movie-ticket booking task with simulated and real users. |
Robust Navigation with Language Pretraining and Stochastic Sampling (D19-1)
Copied to clipboard
Xiujun Li, Chunyuan Li, Qiaolin Xia, Yonatan Bisk, Asli Celikyilmaz, Jianfeng Gao, Noah A. Smith, Yejin Choi
| Challenge: | Existing methods to learn visual representations and action decoding schemes are limited to previously unseen instructions and environments. |
| Approach: | They propose a stochastic sampling scheme to reduce the gap between the expert actions in training and sampled actions in test to correct its own mistakes. |
| Outcome: | The proposed methods achieve 6% absolute gain over the previous best results on the Room-to-Room benchmark. |
ConvLab: Multi-Domain End-to-End Dialog System Platform (P19-3)
Copied to clipboard
Sungjin Lee, Qi Zhu, Ryuichi Takanobu, Zheng Zhang, Yaoqin Zhang, Xiang Li, Jinchao Li, Baolin Peng, Xiujun Li, Minlie Huang, Jianfeng Gao
| Challenge: | ConvLab is an open-source multi-domain end-to-end dialog system platform . it allows researchers to quickly set up experiments with reusable components and compare a large set of different approaches in common environments. |
| Approach: | They propose to use an open-source multi-domain end-to-end dialog system platform to train and evaluate dialog bots in common environments. |
| Outcome: | The proposed system enables researchers to quickly set up experiments with reusable components and compare a large set of different approaches in common environments. |