CHILL

The output produced by WOLFIE can be used to assist a larger language acquisition system; in particular, it is currently used as part of the input to a parser acquisition system called CHILL (Constructive Heuristics Induction for Language Learning). CHILL uses inductive logic programming [Muggleton1992,Lavrac Dzeroski1994] to learn a deterministic shift-reduce parser [Tomita1986] written in Prolog. The input to CHILL is a corpus of sentences paired with semantic representations, the same input required by WOLFIE. The parser learned is capable of mapping the sentences into their correct representations, as well as generalizing well to novel sentences. In this paper, we limit our discussion to CHILL's ability to acquire parsers that map natural language questions directly into Prolog queries that can be executed to produce an answer [Zelle Mooney1996]. Following are two sample queries for a database on U.S. geography, paired with their corresponding Prolog query:

What is the capital of the state with the biggest population?
answer(C, (capital(S,C), largest(P, (state(S), population(S,P))))).

What state is Texarkana located in?
answer(S, (state(S), eq(C,cityid(texarkana,_)), loc(C,S))).

CHILL treats parser induction as the problem of learning rules to control the actions of a shift-reduce parser. During parsing, the current context is maintained in a stack and a buffer containing the remaining input. When parsing is complete, the stack contains the representation of the input sentence. There are three types of operators that the parser uses to construct logical queries. One is the introduction onto the stack of a predicate needed in the sentence representation due to a phrase's appearance at the front of the input buffer. These operators require a semantic lexicon as background knowledge. For details on this and the other two parsing operators, see Zelle (1996). By using WOLFIE, the lexicon is provided automatically. Figure 1 illustrates the

  

Figure 1: The Integrated System

complete system.