Hanlin Teng
Hanlin Teng has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Bin Wang
MiLM Plus Xiaomi Inc Beijing China
2 shared publications - Wei Liu
MiLM Plus Xiaomi Inc
2 shared publications - Hongda Sun
Gaoling School of Artificial Intelligence Renmin University of China
1 shared publication - Jian Luan
MiLM Plus Xiaomi Inc Beijing China
1 shared publication - Jian Luan
Xiaomi AI Lab
1 shared publication - Kang Zhao
Xiaomi AI Lab
1 shared publication
Latest Publications
- 8 October 2023
- Published by Springer Nature
- p. 388-395
Overview of the NLPCC 2023 Shared Task 9: User Feedback Prediction and Response Generation
- 8 October 2023
- Published by Springer Nature
- p. 388-395
Overview of the NLPCC 2023 Shared Task 9: User Feedback Prediction and Response Generation
- Open Access
UniMC: A Unified Framework for Long-Term Memory Conversation via Relevance Representation Learning
Open-domain long-term memory conversation can establish long-term intimacy with humans, and the key is the ability to understand and memorize long-term dialogue history information. Existing works integrate multiple models for modelling through a pipeline, which ignores the coupling between different stages. In this paper, we propose a Unified framework for Long-term Memory Conversations (UniMC), which increases the connection between different stages by learning relevance representation. Specifically, we decompose the main task into three subtasks based on probability graphs: 1) conversation summarization, 2) memory retrieval, 3) memory-augmented generation. Each subtask involves learning a representation for calculating the relevance between the query and memory, which is modelled by inserting a special token at the beginning of the decoder input. The relevance representation learning strengthens the connection across subtasks through parameter sharing and joint training. Extensive experimental results show that the proposed method consistently improves over strong baselines and yields better dialogue consistency and engagingness.
Open AccessUniMC: A Unified Framework for Long-Term Memory Conversation via Relevance Representation Learning
Open-domain long-term memory conversation can establish long-term intimacy with humans, and the key is the ability to understand and memorize long-term dialogue history information. Existing works integrate multiple models for modelling through a pipeline, which ignores the coupling between different stages. In this paper, we propose a Unified framework for Long-term Memory Conversations (UniMC), which increases the connection between different stages by learning relevance representation. Specifically, we decompose the main task into three subtasks based on probability graphs: 1) conversation summarization, 2) memory retrieval, 3) memory-augmented generation. Each subtask involves learning a representation for calculating the relevance between the query and memory, which is modelled by inserting a special token at the beginning of the decoder input. The relevance representation learning strengthens the connection across subtasks through parameter sharing and joint training. Extensive experimental results show that the proposed method consistently improves over strong baselines and yields better dialogue consistency and engagingness.