Towards a Semantic Analysis of Bahasa Indonesia for Question Answering

This paper presents a model of deep syntactic and semantic processing to support question-answering for Bahasa Indonesia. Starting from an existing unification-based grammar, we specify lexical semantics for each lexeme and semantic attachment rules for each grammar rule using lambdacalculus notation. This approach enables us to obtain semantic representations of Indonesian sentences in the form of first order logic literals. These representations are used by a question-answering module which stores declarative sentences as facts in a knowledge-base, and answers queries by unifying the question representation with known facts. We discuss an implemented prototype of this model using Prolog, and conclude with the remaining work that has to be done to realise our goal of a fully-fledged question-answering system for Bahasa Indonesia.