Question-Answering via Enhanced Understanding of Questions.

Abstract

Representation Construction Relation Extraction Question Classification Abstract Representation Construction Relation Extraction Question Set Indexing Extracting Satisfaction Answer Selection Rule-Based R/E Selection Extracting Satisfaction Answer Selection Rule-Based R/E Term Selection and Query Formulation Passage Retrieval Term Selection and Query Formulation Knowledge Base Answer:1559 NYT19990902.0264 Lincoln Memorial Preprocessing Files Question Analysis Record Question Preprocessing Record Indexed Documents Question Analysis Record Retrieved Passages the answer phrase with the top score NE Tagger POS Tagger Shallow Parser NE Tagger POS Tagger Figure 1: System Architecture NE: Who was the [Num first] woman killed in the [Event Vietnam War] ? Like the shallow parser, the named entity recognition process centers around the SNoW based CSCL [ 13 ] , with the addition of some predefined lists for some of the semantic categories. One of the major setbacks in the development of this tool was a lack of su#cient training data. Since our decision process crucially depends on this categorization process, both in question classification and answer selection, we are planning to work on improving the accuracy of this tool.