Sentiment Analysis
Sentiment analysis (SA) studies fundamental problems in entity recognition and sentiment detection. We aim to design systems for extending AI to solve complex natural languages. The ideas are mainly from deep learning, knowledge base and language rules. One of our recent work is to integrate the output of deep neural networks and the implication of linguistic hints into a coherent reasoning model for aspect-level sentiment analysis. We expect the new system can achieve more exceeding performance by integrating more human knowledge.
Entity Resolution based on Human and Machine Cooperation
Pure machine-based solutions usually struggle in challenging classification tasks such as entity resolution (ER). To alleviate this problem, a recent trend is to involve humans in the resolution process, most notably the crowdsourcing approach. We investigate the problem of human and machine cooperation for ER. One of our recent work proposes a novel HUman and Machine cOoperation (HUMO) framework for ER, which divides an ER workload between the machine and the human. HUMO enables a mechanism for quality control that can flexibly enforce both precision and recall levels. Innovatively, we recently investigate the problem of human and machine cooperation for ER from a risk perspective.
Big Data Management System Tools
The big data management system for high-end and manufacturing area is financed by the National Key R&D Program of China, which can collaboratively process various types of data from the industry, such as time series data, structured data, and graph data. We design and implement tools for this system, including integrated resource planning and scheduling tools, automated fault detection and diagnostic tools, and unified data backup and disaster recovery tools. Furthermore, we study optimization algorithms to improve system performance and adaptability, and reduce system operation and maintenance costs.
Data Intensive Computing
Research on massive, distributed, heterogeneous, and continuously changing data computing and the efficiency organization and processing technique on application service environment.