Currently, I am working on neural conversational AI:
natural language understanding: Natural language understanding parses (speech) input to the semantic meaning, including intent classification and slot tagging. The tough challenge is the diversity of natural language and poor supervision resources. Domain adaption and transfer learning are attracting more attention.
dialog policy learning: We take the task-oriented dialogue as the optimal decision-making process to find optimal policy $\pi$, which could be modeled as a typical reinforcement learning(RL) problem. By maximizing average long-term reward, we could learn the optimal action $a$ to state $s$. Although some challenges remain, such as efficient sampling, reward setting, and dialogue evaluation metric, etc.
adversarial learning: Adversarial learning in natural language processing has achieved great success in many aspects, especially for semi-supervision learning, transfer learning from high-resource to low-resource, and active learning, etc. Now I’m focusing on adversarial learning in domain adaption and transfer learning.
- 2018-now, Master in Artificial Intelligence, BEIJING UNIVERSITY OF POSTS AND TELECOMMUNICATIONS
- 2014-2018, Bachelor in Communication Engineering, BEIJING UNIVERSITY OF POSTS AND TELECOMMUNICATIONS
- Research Intern in PRIS LAB, MAR 2017 - SEP 2017
- Maintained and organized the Automatic TaskOriented Dialogue System.
- Research area in task-oriented dialogue system and deep reinforcement learning.
- Research and engineering Intern in GBSAA, IBM, SEP 2017 - FEB 2018
- Research area in object detection and tracking
- Participated in the sports video analysis system of Ministry of Culture and the General Administration of Sport.
- Teamwork with colleagues and mentors in practical and challenging problems.
- Research Intern in SENTINEL TEC, JUL 2018 - SEP 2018
- Research area in dialogue system and knowledge representation.
- Monitored the automatic customer service quality checking system of CHINA CITIC BANK and put into practice.