Donghui Feng

Learning to Detect Conversation Focus of Threaded Discussions

In this paper we present a novel feature-enriched approach that learns to detect the conversation focus of threaded discussions by combining NLP analysis and IR techniques. Using the graph-based algorithm HITS, we integrate different features such as lexical similarity, poster trustworthiness, and speech act analysis of human conversations with feature-oriented link generation functions. It is the first quantitative study to analyze human conversation focus in the context of online discussions that takes into account heterogeneous sources of evidence. Experimental results using a threaded discussion corpus from an undergraduate class show that it achieves significant performance improvements compared with the baseline system.

Intelligent Approaches to Mining the Primary Research Literature: Techniques, Systems, and Examples

In this chapter, we describe how creating knowledge bases from the primary biomedical literature is formally equivalent to the process of performing a literature review or a ‘research synthesis’. We describe a principled approach to partitioning the research literature according to the different types of experiments performed by researchers and how knowledge engineering approaches must be carefully employed to model knowledge from different types of experiment. The main body of the chapter is concerned with the use of text mining approaches to populate knowledge representations for different types of experiment. We provide a detailed example from neuroscience (based on anatomical tract-tracing experiments) and provide a detailed description of the methodology used to perform the text mining itself (based on the Conditional Random Fields model). Finally, we present data from text-mining experiments that illustrate the use of these methods in a real example. This chapter is designed to act as an introduction to the field of biomedical text-mining for computer scientists who are unfamiliar with the way that biomedical research uses the literature.

Handling Biographical Questions with Implicature

Traditional question answering systems adopt the following framework: parsing questions, searching for relevant documents, and identifying/generating answers. However, this framework does not work well for questions with hidden assumptions and implicatures. In this paper, we describe a novel idea, a cascading guidance strategy, which can not only identify potential traps in questions but further guide the answer extraction procedure by recognizing whether there are multiple answers for a question. This is the first attempt to solve implicature problem for complex QA in a cascading fashion using N-gram language models as features. We here investigate questions with implicatures related to biography facts in a web-based QA system, Power-Bio. We compare the performances of Decision Tree, Naive Bayes, SVM (Support Vector Machine), and ME (Maximum Entropy) classification methods. The integration of the cascading guidance strategy can help extract answers for questions with implicatures and produce satisfactory results in our experiments.

Adaptive Information Extraction for Complex Biomedical Tasks

Biomedical information extraction tasks are often more complex and contain uncertainty at each step during problem solving processes. We present an adaptive information extraction framework and demonstrate how to explore uncertainty using feedback integration.