Our purpose in studying natural language understanding in conjunction with problem solving is to bring together the constraints of what formal representation can actually be obtained with the question of what knowledge is required in order to solve a wide range of problems in a semantically rich domain. We believe that these issues cannot sensibly be tackled in isolation. In practical terms we have had the benefits of an increased awareness of common problems in both areas and a realisation that some of our techniques are applicable to both the control of inference and the control of parsing. Early work on solving mathematical problems stated in natural language was done by Bobrow (STUDENT - (i]) and Chamiak (CARPS - [5]). However the rudimentary parsing and simple semantic structures used by Bobrow and Charniak are inadequate for any but the easiest problems. Our intention has been to build on B/RG Chris This work was supported by SRC grant number 94493 and an SRC research studentship for Mellish.

Artificial Intelligence, vol. 9, pp. 287-306.

Lingua, vol. 44, pp. 311-338. Also in Readings in Natural Language Processing, B. Grosz, K. Sparck-Jones, and B. Webber, editors, pp. 339-352, Morgan Kaufmann Publishers, Los Altos, California.

Proc. IJCAI 77 VOL 1 MASSACHUSETTS INSTITUTE OF TECHNOLOGY CAMBRIDGE, MASSACHUSETTS, USA AUGUST 22 - 25 , 1977, pp.286-291.

Proc. IJCAI 77 VOL 1 MASSACHUSETTS INSTITUTE OF TECHNOLOGY CAMBRIDGE, MASSACHUSETTS, USA AUGUST 22 - 25 , 1977.

Also found at aminer.orgProc. IJCAI 77 VOL 1 MASSACHUSETTS INSTITUTE OF TECHNOLOGY CAMBRIDGE, MASSACHUSETTS, USA AUGUST 22 - 25 , 1977, pp.43-49

Proc. IJCAI 77 VOL 1 MASSACHUSETTS INSTITUTE OF TECHNOLOGY CAMBRIDGE, MASSACHUSETTS, USA AUGUST 22 - 25 , 1977, pp. 183-191.

This paper describes a computer system for understanding English. The system answers questions, executes commands, and accepts information in an interactive English dialog. It is based on the belief that in modeling language understanding, we must deal in an integrated way with all of the aspects of language—syntax, semantics, and inference. The system contains a parser, a recognition grammar of English, programs for semantic analysis, and a general problem solving system. We assume that a computer cannot deal reasonably with language unless it can understand the subject it is discussing. Therefore, the program is given a detailed model of a particular domain.

Lexical ambiguity can be syntactic if it involves more than one grammatical category for a single word, or semantic if more than one meaning can be associated with a word. In this article we discuss the application of a Bayesian-network model in the resolution of lexical ambiguities of both types. The network we propose comprises a parsing subnetwork, which can be constructed automatically for any context-free grammar, and a subnetwork for semantic analysis, which, in the spirit of Fillmore's (1968) case grammars, seeks to fulfill the required cases of all candidates for verb of the sentence. Solving for the highest joint probability of the variables conditioned upon the evidences to the network yields the most likely candidate with its meaning, along with its cases and respective meanings. This is achieved by fixing the values of all evidence nodes concurrently, and then performing a stochastic simulation in which the remaining nodes are updated probabilistically with a high degree of parallelism.

We present a novel statistical approach to semantic parsing, WASP, for constructing a complete, formal meaning representation of a sentence. A semantic parser is learned given a set of sentences annotated with their correct meaning representations. The main innovation of WASP is its use of state-of-the-art statistical machine translation techniques. A word alignment model is used for lexical acquisition, and the parsing model itself can be seen as a syntax-based translation model. We show that WASP performs favorably in terms of both accuracy and coverage compared to existing learning methods requiring similar amount of supervision, and shows better robustness to variations in task complexity and word order.