Carl Weir

Efficiency, Robustness and Accuracy in picky Chart Parsing

This paper describes Picky, a probabilistic agenda-based chart parsing algorithm which uses a technique called probabilistic prediction to predict which grammar rules are likely to lead to an acceptable parse of the input. Using a suboptimal search method, Picky significantly reduces the number of edges produced by CKY-like chart parsing algorithms, while maintaining the robustness of pure bottom-up parsers and the accuracy of existing probabilistic parsers. Experiments using Picky demonstrate how probabilistic modelling can impact upon the efficiency, robustness and accuracy of a parser.

The PUNDIT natural-language processing system

The authors describe the PUNDIT (Prolog Understanding of Integrated Text) text-understanding system, which is designed to analyze and construct representations of paragraph-length text. PUNDIT is implemented in Quintus Prolog, and consists of distinct lexical, syntactic, semantic, and pragmatic components. Each component draws on one or more sets of data, including a lexicon, a broad-coverage grammar of English, semantic verb decompositions, rules mapping between syntactic and semantic constituents, and a domain model. Modularity, careful separation of declarative and procedural information, and separation of domain-specific and domain-independent information all contribute to a system which is flexible, extensible and portable. Versions of PUNDIT are now running in five domains, including four military and one medical.<<ETX>>

Answers and questions: processing messages and queries

This paper describes issues in adapting the PUNDIT system, designed originally for message processing, to a query-answering system for the VOYAGER application. The resulting system, whose architecture and capabilities are described here, represents a first step towards our goal of demonstrating spoken language understanding in an interactive problem-solving context.

An intelligent document understanding system

Starting with scanned image(s) of a documents pages (either from hardcopy or from a fax source), the authors attempt to produce document representations which can be stored in a database which then supports a variety of document understanding applications. Current work to develop an intelligent document understanding system prototype, aimed towards this goal, is described.<<ETX>>

Probabilistic prediction and P icky chart parsing

This paper describes Picky, a probabilistic agenda-based chart parsing algorithm which uses a technique called probabilistic prediction to predict which grammar rules are likely to lead to an acceptable parse of the input. In tests on randomly selected test data, Picky generates fewer edges on average than other CKY-like algorithms, while achieving 89% first parse accuracy and also enabling the parser to process sentences with false starts and other minor disfluencies. Further, sentences which are parsed completely by the probabilistic prediction technique have a 97% first parse accuracy.

Integrated text and image understanding for document understanding

Because of the complexity of documents and the variety of applications which must be supported, document understanding requires the integration of image understanding with text understanding. Our document understanding technology is implemented in a system called IDUS (Intelligent Document Understanding System), which creates the data for a text retrieval application and the automatic generation of hypertext links. This paper summarizes the areas of research during IDUS development where we have found the most benefit from the integration of image and text understanding.

Integrating Natural Language Understanding with Document Structure Analysis

Document understanding, the interpretation of a document from its image form, is a technology area which benefits greatly from the integration of natural language processing with image processing. We have developed a prototype of an Intelligent Document Understanding System (IDUS) which employs several technologies: image processing, optical character recognition, document structure analysis and text understanding in a cooperative fashion. This paper discusses those areas of research during development of IDUS where we have found the most benefit from the integration of natural language processing and image processing: document structure analysis, optical character recognition (OCR) correction, and text analysis. We also discuss two applications which are supported by IDUS: text retrieval and automatic generation of hypertext links

Porting PUNDIT to the resource management domain

This paper describes our experiences porting the PUNDIT natural language processing system to the Resource Management domain. PUNDIT has previously been applied to a range of messages (see the paper Analyzing Explicitly Structured Discourse in a Limited Domain: Trouble and Failure Reports by C. Ball (appearing in this volume), and also [Hirschman1989]. However, it had not not been tested on any significant corpus of queries, such as that represented by the Resource Management corpus. Our goal was to assess PUNDITs portability, and to determine its coverage of syntax over this domain. Time constraints precluded testing of the semantic component, but we plan to report on this at subsequent meetings. We performed this port with the intention of coupling PUNDIT to the MIT SUMMIT speech recognition system. This work is described in another paper in this volume, Reducing Search by Partitioning the Word Network, by J. Dowding.

Unisys: description of the Unisys system used for MUC-3

This paper describes the Unisys MUC-3 text understanding system, a system based upon a three-tiered approach to text processing in which a powerful knowledge-based form of information retrieval plays a central role. This knowledge-based form of information retrieval makes it possible to define an effective level of text analysis that falls somewhere between what is possible with standard keyword-based information retrieval techniques and deep linguistic analysis.

A methodology for application development for spoken language systems

A major bottleneck in the development of practical spoken language (SL) applications is the interface between the SL system and back-end application software. In theory, the range of potential back-end software for an SL interface is unlimited, but integration of an SL system with other software requires adapting the SL system to conform to the input formats of the back end. This is typically accomplished by ad hoc, labor-intensive methods, which are highly application-specific. Some SL systems have addressed this problem by attempting to handle only relational database interface applications, but this approach limits the usefulness of such systems, since relational databases represent only a fraction of the applications which could benefit from an SL interface. This paper describes a general, flexible, rule-based approach to integrating SL applications to arbitrary back-end software.