This paper introduces a paradigm of context-dependent grammar (CDG) and an acquisition system that, through interactive teaching sessions, accumulates the CDG rules. The resulting context-sensitive rules are used by a stack-based, shift/reduce parser to compute unambiguous syntactic structures of sentences. The acquisition system and parser have been applied to the phrase structure and case analyses of 345 sentences, mainly from newswire stories, with 99% accuracy. Extrapolation from our current grammar predicts that about 25 thousand CDG rule examples will be sufficient to train the system in phrase structure analysis of most news stories. Overall, this research concludes that CDG is a computationally and conceptually tractable approach for the construction of sentence grammar for large subsets of natural language text.

A system is described for acquiring a context-sensitive, phrase structure grammar which is applied by a best-path, bottom-up, deterministic parser. The grammar was based on English news stories and a high degree of success in parsing in reported. Overall, this research concludes that CSG is a computationally and conceptually tractable approach to the construction of phrase structure grammar for news story text.

There are two measures for the optimality of a trained feedforward network for the given training patterns: the global error function and the correctness ratio. In the present work, the authors argue that these two measures are not parallel and present a technique (called descending epsilon) with which the back-propagation method results in a high correctness ratio. It is shown that, with this technique, the trained networks often exhibit high correctness ratios not only for the training patterns but also for novel patterns

In this paper, we present a computational method for transforming a syntactic graph, which represents all syntactic interpretations of a sentence, into a semantic graph which filters out certain interpretations, but also incorporates any remaining ambiguities. We argue that the resulting ambiguous graph, supported by an exclusion matrix, is a useful data structure for question answering and other semantic processing. Our research is based on the principle that ambiguity is an inherent aspect of natural language communication.

Understanding a text requires two basic tasks: making inferences at several levels of knowledge and composing a global interpretation of the given text from those various types of inferences. Since making inferences at each level demands an extensive computations, there have been several attempts to use parallel inference mechanisms such as parallel marker passing (PMP) to increase the productivity of the inference mecha nism. Such a mechanism, when used with many local processors, is capable of making inferences in parallel. However, it often poses a large burden on the task of composing the global interpretation by producing a number of meaningless inferences which should be filtered out. Therefore, the increased productivity of the inference mechanism causes the slow down of the task of forming the global interpretation and makes it the bottleneck of the whole system. Our system, TRUE, effectively solves this problem with the Constrained Marker Passing mechanism. The new mechanism not only allows the system to make necessary inferences in parallel, but also provides a way to compose the global interpretation in parallel. Therefore, the system is truly parallel, and does not suffer from any single bottleneck.

This research aims at defining a consistent set of text representation conventions for organizing fifty pages of the AI handbook as an inferential knowledge base founded on a procedural logic system of general inference schemes for answering questions from it. As a result of research on the AI handbook project, we have developed a prototype, natural-language, text-knowledge system that includes a data base manager to compile the text knowledge and to make it available to navigational commands. The text is represented as logical propositions that form a set of text axioms to model its content. English questions and commands are translated to corresponding logical formulas and treated as theorems to be proved with respect to the text model. The logical form is that of semantic relations (SRs)—logical predicates with varying numbers and ordering of arguments. To compute effectively with such a free form, a relaxed unification procedure was defined as the basis of the SR theorem prover. The use of procedural logic, augmented with fast compiled LISP functions, has shown that questions can be answered in times ranging from a few tenths of a second to minutes of CPU time on a DEC2060 system. The navigational capabilities of the data base manager make available larger contexts surrounding the text and offer the user complete freedom to explore the text and to extract any desired information from it.

In this paper, we present a new method of representing the surface syntactic structure of a sentence. Trees have usually been used in linguistics and natural language processing to represent syntactic structures of a sentence. A tree structure shows only one possible syntactic parse of a sentence, but in order to choose a correct parse, we need to examine all possible tree structures one by one. Syntactic graph representation makes it possible to represent all possible surface syntactic relations in one directed graph (DG). Since a syntactic graph is expressed in terms of a set of triples, higher level semantic processes can access any part of the graph directly without navigating the whole structure. Furthermore, since a syntactic graph represents the union of all possible syntactic readings of a sentence, it is fairly easy to focus on the syntactically ambiguous points. In this paper, we introduce the basic idea of syntactic graph representation and discuss its various properties. We claim that a syntactic graph carries complete syntactic information provided by a parse forest---the set of all possible parse trees.

A modern computing system includes hundreds For those who have no desire to program, the Apple of operators and programs, each with its own MacIntosh is ideal. It is essentially a desk assistant with a control language. A technological marvel for one-button mouse and hierarchies of menus. The bit-map information processing, it asks only that we display offers a large set of options for drawing, text prepfigure out how to use it in achieving our goals. Unfortuaration, editing, type-setting, and the display, and printing nately, all too often, the description and documentation of of data. One or two hour's experience with such a system such a system entails several fat volumes of difficult text, is sufficient to enable most of the uninitiated to graduate so we frequently settle for using the system in limited ways from a typewriter to a high-technology information control t( avoid the extensive effort required to learn it thoroughly. device. The Macintoshes of the world not only replace the Fortunately, help is on the way. The best equipped modprinting functions of the typewriter, but add capabilities ern laboratories now have specialized workstations such as for drawing diagrams and artwork, for storing files, for Lisp machines and Suns. These large, fast microcomputers graphically displaying and charting data, and for dabbling are supported by megabytes of internal memory, hundreds in an endless variety of creative activities. As long as we of megabytes of local disk storage, and, lurking in the are content with the capabilities provided by the menus, we background, a gigantic file server, providing trillions of are almost fully protected from asking impossible quesmegs of long-term memory, not to mention network comtions-only meaningful sequences of menu choices are promunications with the world. vided-and the system is equally protected from our wellBut wait, there's more. There are bit-map displays on meaning, but occasionally disastrous, efforts. the order of 1000 x 1000 pixels and a mouse whose moIn general, the operating system, whether controlled by tion translates into movements of a pointer on the display. mouse and menu or by formal language commands, proBy merely pushing one or more buttons on top of the vides a set of operations that users can combine to accommouse, we can select a portion of the screen (actually of plish a set of information processing goals. These goals, the array that the screen displays) to focus on specific data. with careful design and a bit of luck, will represent what The most common use of the mouse, however, is to select the system understands of user intentions. From a user a choice from a menu. The pointer is guided to one of the viewpoint, these operations are primitives at the bottom of choices displayed on the screen, a button is pressed on the the human goal system. mouse, and the system passes control to the procedure seIn menu-controlled systems, possible processing goals are lected from the menu. This procedure may present addicompletely prespecified. Users need only select a permissitional menus or actually accomplish some task. ble sequence to accomplish their goals. In formal-language A menu is usually a box drawn on the screen containing controlled systems, the user may be offered much more cells with the names of the procedures that can be selected, freedom in accomplishing goals within the capability of the although it may take other display forms such as a boxed system, but at the cost of learning several formal command border of the screen in which choices are shown. languages at the operating system and production program

A system of grammars using symmetric phrase structure and translation rules in a Lisp version of Prolog is shown to provide symmetric bidirectional translation between English and Chinese for a fragment of the two languages. It is argued that symmetric grammars and translation rules significantly reduce the total grammar writing requirement for translation systems, and that research on symmetric translation systems deserves further study.