Reasoning about Document Collections

RDC

About RDC

Research

This project is no longer active, although the research areas are still relevant for many NLTT projects.

Research in the Reasoning about Document Collections (RDC) project focused on developing computational tools and methodologies for accessing information contained in domain-focused document collections. While current tools recognize what documents are about, RDC worked toward the development of new generations of knowledge-based tools that could interpret the meaning of the documents' content.

RDC explored new techniques for analyzing natural language texts and producing conceptual representations of their content. Their work combined deep parsing techniques for linguistic analysis, language semantics and general and domain-specific knowledge representation and inference. RDC engaged in basic research aimed at solving fundamental problems of symbolic natural language understanding, challenging the conventional wisdom that it is not possible to automatically produce useful representations of document content using symbolic natural language processing (NLP).

This work drew on recent technological advances that are making the use of NLP techniques more commercially feasible. It also drew on the XLE Linguistic Environment a proprietary set of technologies based on PARC's world-class competency in NLP. The RDC research team included computer scientists and linguists with expertise in computational linguistics, symbolic processing of language, mathematical logic, artificial intelligence, knowledge representation, and automated reasoning. They explored three key research areas:

Press Reports

Participants

Natural Language Theory and Technologies group (NLTT) of the Intelligent Systems Lab (ISL)

Selected Publications


Last modified: