2012 QuestionAnalysisHowWatsonReadsa
- (Lally et al., 2012) ⇒ Adam Lally, JM Prager, MC McCord, BK Boguraev, Siddharth Patwardhan, James Fan, Paul Fodor, and Jennifer Chu-Carroll. (2012). “Question Analysis: How Watson Reads a Clue.” In: IBM Journal of Research and Development, 56(3-4).
Subject Headings: LAT; Watson QA System
Notes
Cited By
Quotes
Abstract
The first stage of processing in the IBM WatsonTM system is to perform a detailed analysis of the question in order to determine what it is asking for and how best to approach answering it. Question analysis uses Watson’s parsing and semantic analysis capabilities: a deep Slot Grammar parser, a named entity recognizer, a co-reference resolution component, and a relation extraction component. We apply numerous detection rules and classifiers using features from this analysis to detect critical elements of the question, including: 1) the part of the question that is a reference to the answer (the focus); 2) terms in the question that indicate what type of entity is being asked for (lexical answer types); 3) a classification of the question into one or more of several broad types; and 4) elements of the question that play particular roles that may require special handling, for example, nested subquestions that must be separately answered. We describe how these elements are detected and evaluate the impact of accurate detection on our end-to-end question-answering system accuracy
1. Introduction
…
... LATs are terms in the question that indicate what type of entity is being asked for. The headword of the focus is generally a LAT, but questions often contain additional LATs, and in the Jeopardy! domain, categories are an additional source of LATs. In the example, LATs are "he", "clerk", and "poet". LATs are used by Watson’s type coercion components [2] to determine whether a candidate answer is an instance of the answer types
References
,