Exploiting Syntactic and Shallow Semantic Kernels to Improve Random Walks for Complex Question Answering

We consider the problem of answering complex questions that require inferencing and synthesizing information from multiple documents and can be seen as a kind of topic-oriented, informative multi-document summarization. The stochastic, graph-based method for computing the relative importance of textual units (i.e. sentences) is very successful in generic summarization. In this method, a sentence is encoded as a vector in which each component represents the occurrence frequency (TF*IDF) of a word. However, the major limitation of the TF*IDF approach is that it only retains the frequency of the words and does not take into account the sequence, syntactic and semantic information. In this paper, we study the impact of syntactic and shallow semantic information in the graph-based method for answering complex questions. Experimental results show the effectiveness of the syntactic and shallow semantic information for this task.