Search

Recent experiments in programming natural language question-answering systems are reviewed to summarize the methods that have been developed for syntactic, semantic, and logical analysis of English strings. It is concluded that at least minimally effective techniques have been devised for answering questions from natural language subsets in small scale experimental systems and that a useful paradigm has evolved to guide research efforts in the field. Current approaches to semantic analysis and logical inference are seen to be effective beginnings but of questionable generality with respect either to subtle aspects of meaning or to applications over large subsets of English. Generalizing from current small-scale experiments to language-processing systems based on dictionaries with thousands of entries-with correspondingly large grammars and semantic systems-may entail a new order of complexity and require the invention and development of entirely different approaches to semantic analysis and question answering. [ABSTRACT FROM AUTHOR]

The use of augmented transition network grammars for the analysis of natural language sentences is described. Structure-building actions associated with the arcs of the grammar network allow for the reordering, restructuring, and copying of constituents necessary to produce deep-structure representations of the type normally obtained from a transformational analysis, and conditions on the arcs allow for a powerful selectivity which can rule out meaningless analyses and take advantage of semantic information to guide the parsing. The advantages of this model for natural language analysis are discussed in detail and illustrated by examples. An implementation of an experimental parsing system for transition network grammars is briefly described. [ABSTRACT FROM AUTHOR]

The Teachable Language Comprehender (TLC) is a program designed to be capable of being taught to "comprehend" English text. When text which the program has not seen before is input to it, it comprehends that text by correctly relating each (explicit or implicit) assertion of the new text to a large memory. This memory is a "semantic network" representing factual assertions about the world. The program also creates copies of the parts of its memory which hove been found to relate to the new text, adapting and combining these copies to represent the meaning of the new text. By this means, the meaning of all text the program successfully comprehends is encoded into the same format as that of the memory. In this form it can be added into the memory. Both factual assertions for the memory and the capabilities for correctly relating text to the memory's prior content are to be taught to the program as they are needed. TLC presently contains a relatively small number of examples of such assertions and capabilities, but within the system, notations for expressing either of these are provided. Thus the program now corresponds to general process for comprehending language, and it provides methodology for adding the additional information this process requires to actually comprehend text of any particular kind. The memory structure and comprehension process of TLC allow new factual assertions and capabilities for relating text to such stored assertions to generalize automatically. That is, once such an assertion or capability is put into the system, it becomes available to help comprehend a great many other sentences in the future. Thus the addition of a single factual assertion or linguistic capability will often provide large increment in TLC's effective knowledge of the world and in its overall ability to comprehend text. The program's strategy is presented as a general theory of language comprehension. [ABSTRACT FROM AUTHOR]

A further development of a computer program (ELIZA) capable of conversing in natural language is discussed. The importance of context to both human and machine understanding is stressed. It is argued that the adequacy of the level of understanding achieved in a particular conversation depends on the purpose of that conversation, and that absolute understanding on the part of either humans or machines is impossible. [ABSTRACT FROM AUTHOR]

MUSE is a computer model for natural language processing, based on a semantic memory network like that of Quillian's TLC. MUSE, from a Model to Understand Simple English, processes English sentences of unrestricted content but somewhat restricted format. The model first applies syntactic analysis to eliminate some interpretations and then employs a simplified semantic intersection procedure to find a valid interpretation of the input. While the semantic processing is similar to TLC's, the syntactic component includes the early use of parse frees and special purpose rules. The "relational triple" notation used during interpretation of input is compatible with MUSE's memory structures, allowing direct verification of familiar concepts and the addition of new ones. MUSE also has a repertoire of actions, which range from editing and reporting the contents of its own memory to an indirect form of question answering. Examples are presented to demonstrate how the model interprets text, resolves ambiguities, adds information to memory, generalizes from examples, and performs various actions. [ABSTRACT FROM AUTHOR]