Showing papers on "Question answering published in 1976"

On natural language based computer systems

Abstract: Some of the arguments that have been given both for and against the use of natural languages in question-answering and programming systems are discussed. Several natural language based computer systems are considered in assessing the current level of system development. Finally, certain pervasive difficulties that have arisen in developing natural language based systems are identified, and the approach taken to overcome them in the REQUEST (Restricted English QUESTion-Answering) System is described.

From text to structured information: automatic processing of medical reports

Abstract: This paper describes the analysis and processing programs for a set of natural language texts in a medical area (x-ray reports on patients with breast cancer). The programs convert the information in the text into a tabular form suitable for further automatic information processing (e.g., editing of records, question answering on the data collected, or statistical summaries of the data). To set up a tabular form appropriate for the data, we first perform a manual linguistic analysis on a sample of the texts. From this we obtain the word classes and the form of the table (called an information format) for this type of material. We then apply the series of processing programs to the sentences of the texts. Each sentence is parsed with the Linguistic String Parser English grammar in order to obtain its grammatical structure; certain standard English transformations are then applied to regularize the grammatical form of the sentence; and finally a set of "formatting transformations" map the words of the sentence into the slots of the format or table, in such a way that the sentence is reconstructible (up to paraphrase) from its representation in the table. The results of applying these programs to a corpus are described. This procedure enables us to convert a natural language corpus into a structured data base.

Using plans to understand natural language

Abstract: Our ability to build a natural language understanding system is limited by the degree to which we can organize and apply world knowledge. This paper describes a program, called PAM, that has knowledge about people's intentions. PAM uses its knowledge to infer the relationships between sentences in a text. A sample run of the program is presented and is described in detail. The inference mechanisms of PAM are compared to those of other knowledge-application programs.

Semantic Modeling for Deductive Question-Answering

Abstract: A description of techniques used for semantic modeling in a deductive question-answering system is given. The system maintains a dialog and is able to understand situations which can be expressed as a series of sequential time-frames. Specific relevant questions are asked by the system when it is unable to succeed in a given task. It can also provide reasons for its previous actions.

Inferential question answering in a textual data base

Abstract: A paragraph of expository text is presented in case predicate and semantic network form as an example of a textual data base. An inferential procedure that has been used to answer questions from case predicate structures is outlined. It is argued that case predicates and their corresponding graphic form, semantic networks, are variant notations convenient to represent and compute the logical relations that hold among conceptual elements in English texts.