Jianyong Duan

Learn More
Traditional text categorization is usually a topic-based task, but a subtle demand on information retrieval is to distinguish between positive and negative view on text topic. In this paper, a new method is explored to solve this problem. Firstly, a batch of Concerned Concepts in the researched domain is predefined. Secondly, the special knowledge(More)
This paper proposes a new approach for Multi-word Expression (MWE)extraction on the motivation of gene sequence alignment because textual sequence is similar to gene sequence in pattern analysis. Theory of Longest Common Subse-quence (LCS) originates from computer science and has been established as affine gap model in Bioinformatics. We perform this(More)
This paper presents a language modeling approach to the sentiment detection problem. It captures the subtle information in text processing to character the semantic orientation of documents as " thumb up " (positive) or " thumb down " (negative). To handle this problem, we propose an idea to estimate both the positive and negative language models from(More)
In this paper, we present a weakly supervised learning approach for spoken language understanding in domain-specific dialogue systems. We model the task of spoken language understanding as a successive classification problem. The first classifier (topic classifier) is used to identify the topic of an input utterance. With the restriction of the recognized(More)
Word sense disambiguation is a technology of judging the specific semantic of polysemous words in the specific context. It is meaningful for the applications of natural language processing. This paper introduces the attribute knowledge into word sense disambiguation task. Every sense of the polysemous words can be described by the different attribute sets.(More)
For the Multiword Expression (MWE) recognition, the Multiple Sequence Alignment (MSA) is proposed on the motivation of gene recognition. Because textual sequence is similar to gene sequence in pattern analysis. This MSA technique is combined with error-driven rules, with the improved efficiency beyond the traditional methods.It provides a guarantee for the(More)