Interested in better understanding the discussions among your students? Would you like to support your students during reflection? This research demonstrates semantic analysis of students’ discussions, which can be used to provide appropriate help to the students in real-time.
This demonstration will show the on-going research and development of natural language processing (NLP) enhanced search engine and automated question answering (QA) systems, which underlie Questions/Answers (Q&A) Services in the NSERC/iCORE research program. The demonstration includes five small demos. The first one shows the use of an NLP server for deeper question analysis in a search engine like question answering application designed for facilitating students’ access and retrieval of knowledge and information from the learning materials in the form of natural language text. The second demo shows how NLP parsing tools, including Xerox’s XIP, analyze natural language sentences, and thus provide information for further understanding of the natural language questions and answers. In the third demo, an interface of our NLP based QA system will be presented to show the main underlying processes step by step, from a user query, syntactic parsing, to semantic analysis, searching and matching, and final lead to the possible answer sets of the query. The last two demos are experiments on semantic analysis and feature learning for automated question answering respectively. They evaluate the performance of our methods for a set of test sentences against the test corpora, and serve as platforms for us to develop effective Q&A Services of the research program.
D. Wen, S. Jiang, and Y. He, “A Question Answering System based on VerbNet Frames”, Proceedings of the IEEE International Conference on Natural Language Processing and Knowledge Engineering (IEEE NLP-KE’08), Oct. 2008, Beijing, China.