Relevance helps identify to what extent a review's content pertains to that of the submission. Relevance metric helps distinguish generic or vague reviews from the useful ones. Relevance of a review to a submission can be determined by identifying semantic and syntactic similarities between them. Our work introduces the use of a word-order graph…

For over 30 years, reference resolution, the process of determining what a noun phrase including a pronoun refers to in written and spoken language, has been an important and on-going area of research. Most existing pronominal reference resolution algorithms and systems are designed to use syntactic information and surface features (e.g. number…

Ways of making the natural language of unsophisticated computer users meaningful to the computer are discussed. The discussion is set within the context of the Rapidly Extensible Language (REL) System, a question answering system with underlying relational data bases. Major topics covered include individuals and predicates, the problem of verbs,…

The nature of computational linguistics, and formulation of problems in literary analysis to which this approach can be applied, are considered. A review of current work in this field and an illustration of how this work might be used in an analysis of Shakespeare's writing are presented. (RW)

This paper attempts to characterize some of the knowledge that people have of their language's semantic structure, in order to determine what a computer has to know to perform the operations of searching for facts and answering questions. Necessarily, this sort of semantic analysis is done in connection with syntactic structure. The meaningful…

When a grammar is expressed in augmented transition network (ATN) form, the problem of detecting syntactic ambuguity reduces to finding all possible paths through the ATNs. Each successfully terminating path through the ATN generates an acceptable parsing of the input string. Two ATN forms, minimal-node and pseudo-tree, are described along with…

The paper surveys the major projects on the understanding of natural language that fall within what may now be called the artificial intelligence paradigm of natural language systems. Some space is devoted to arguing that the paradigm is now a reality and different in significant respects from the generative paradigm of present-day linguistics.…

This is a description of the motivation and overall organization of the OWL language for knowledge representation. OWL consists of a linguistic memory system (LMS), a memory of concepts in terms of which all English phrases and all knowledge of an application domain are represented; a theory of English grammar which tells how to map English…

For the past 15 years there has been a serious interest in the processing of natural language (English) by researchers in Artificial Intelligence (A.I.). This processing has included machine translation, question-answering systems, man-machine dialogue, and speech understanding. This interest has engendered an awareness of and a concern with the…

This report is the third in a series of annual reports describing the research performed by Stanford Research Institute to provide the technology that will allow speech understanding systems to be designed and implemented for a variety of different task domains and environmental constraints. The current work is being carried out cooperatively with…

This second volume of a two-volume report on a fully automatic high quality translation (FAHQT) contains relevant papers contributed by specialists on the topic of machine translation. The papers presented here cover such topics as syntactical analysis in transformational grammar and in machine translation, lexical features in translation and…

The objective of this thesis was to colligate the various strands of research in the literature of computational linguistics that have to do with the computational treatment of semantic content so as to encode it into a computerized dictionary. In chapter 1 the course of mechanical translation (1947-1960) and quantitative linguistics is traced to…

This bibliography, prepared and stored on a computer, is intended to aid in locating works on the semantics of human language. As a reference bibliography, it presents as many different places and modes of publication as possible, and includes as wide a range of subjects as possible. It is intended to cover all of linguistic semantics, with…

This document contains the reports summarizing the main discussion held during the March 1972 Computational Linguistics Conference. The first report, "Computational Linguistics and Linguistics," helps to establish definitions and an understanding of the scope of computational linguistics. "Integrated Computer Systems for Language" and…

QUE2 is a recently devised, natural language, questioning-answering program written in LISP1-5. It deals in simple, kernel sentences and employs the theory that the semantic content of a sentence is the set of relationships between conceptual objects (represented by the words in it), which the sentence and its structure imply. The data base of the…