Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2022-11-27 Cooperative journals: 《数据智能（英文）》
Jian, Yuan
Zhongyu, Wei
Yixu, Gao
Wei, Chen
Yun, Song
Donghua, Zhao
Jinglei, Ma
Zhen, Hu
Shaokun, Zou
Donghai, Li
Xuanjing, Huang
Abstract： In this paper we present the results of the Interactive Argument-Pair Extraction in Judgement Document Challenge held by both the Chinese AI and Law Challenge (CAIL) and the Chinese National Social Media Processing Conference (SMP), and introduce the related data set – SMP-CAIL2020-Argmine. The task challenged participants to choose the correct argument among five candidates proposed by the defense to refute or acknowledge the given argument made by the plaintiff, providing the full context recorded in the judgement documents of both parties. We received entries from 63 competing teams, 38 of which scored higher than the provided baseline model (BERT) in the first phase and entered the second phase. The best performing system in the two phases achieved accuracy of 0.856 and 0.905, respectively. In this paper, we will present the results of the competition and a summary of the systems, highlighting commonalities and innovations among participating systems. The SMP-CAIL2020-Argmine data set and baseline models have been already released.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2022-11-27 Cooperative journals: 《数据智能（英文）》
Abstract： One of the major challenges to build a task-oriented dialogue system is that dialogue state transition frequently happens between multiple domains such as booking hotels or restaurants. Recently, the encoder#2;decoder model based on the end-to-end neural network has become an attractive approach to meet this challenge. However, it usually requires a sufficiently large amount of training data and it is not flexible to handle dialogue state transition. This paper addresses these problems by proposing a simple but practical framework called Multi-Domain KB-BOT (MDKB-BOT), which leverages both neural networks and rule#2;based strategy in natural language understanding (NLU) and dialogue management (DM). Experiments on the data set of the Chinese Human-Computer Dialogue Technology Evaluation Campaign show that MDKB#2;BOT achieves competitive performance on several evaluation metrics, including task completion rate and user satisfaction.
Subjects: Physics >> General Physics: Statistical and Quantum Mechanics, Quantum Information, etc. Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2017-03-15
Abstract：As the next stage of Artificial Intelligence, Brain-like Intelligent Computing will be considered as a fundamental role in the forthcoming China Brain Project. Researchers have tried to use the brain frame structure and the brain functions, aiming at developing a new generation of information theory and computational methods (such as a new generation of artificial intelligence systems). Different from the traditional information processing based on the classical physics and logics, the human brain should rely on a deeper level physics (such as quantum mechanics) to process information, generate awareness and consciousness. The project will try to exploit quantum information theory in the human cognition related information interaction and processing models. The overall research goal is: in typical information interaction scenarios (such as exploratory information access and natural language understanding), modeling the non-classical (quantum or quantum-like) experimental phenomenon, developing quantum models of cognitive behavior, and establishing a new framework of brain-like information interaction model, with the application in typical tasks for information interaction scenarios.
Peer Review Status:
Awaiting Review
Hits
Hits
Downloads
Comment