PROTEUS and PUNDIT: Research in Text Understanding

نویسندگان

  • Ralph Grishman
  • Lynette Hirschman
چکیده

We are engaged in the deve lopment of systems capable of analyzing short narrat ive messages dealing with a limited domain and extract ing the informat ion conta ined in the narrat ive. These systems are initially being applied to messages describing equ ipmen t failure. This work is a joint e f fo r t of New York Universi ty and the System Deve lopmen t Corp . for the Strategic Computing Program. Our aim is to create a system reliable enough for use in an operat ional envi ronment . This is a formidable task, both because the texts are unedi ted (and so contain various errors) and because the complexi ty of any real domain precludes us from assembling a "complete" collection of the relationships and domain knowledge relevant to understanding texts in the domain.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Recovering Implicit Information

This paper describes the SDC PUNDIT, (Prolog UNDerstands Integrated Text), system for processing natura l language messages. 1 PUNDIT, written in Prolog, is a highly modular system consisting of distinct syntactic, semantic and pragmatics components. Each component draws on one or more sets of data, including a lexicon, a broad-coverage grammar of EngLish, semantic verb decompositions, rules ma...

متن کامل

Unisys: MUC-3 test results and analysis

[A Linguistic Analysis Component . ] Although a natural language processing component was included in the design of the Unisys MUC-3 system as a third level of text analysis, not enough time was availabl e during the MUC-3 development cycle both to develop a knowledge-based information retrieval component and to port the Unisys Pundit text-processing system to the MUC 3 terrorist domain . A dec...

متن کامل

Linguistic Knowledge Sources for Spoken Language Understanding

The objective of the Unisys Spoken Language Systems effort is to develop and demonstra te technology for the understanding of goal-directed spontaneous speech. The Unisys spoken language architecture couples speech recognition systems with the Unisys discourse understanding system, PUNDIT. PUNDIT is a broad-coverage language understanding system used in a variety of message understanding applic...

متن کامل

Project Summary: Linguistic Knowledge Sources for Spoken Language Understanding

The objective of the Unisys Spoken Language Systems effort is to develop and demonstrate technology for the understanding of goal-directed spontaneous speech input. The Unisys spoken language architecfure couples a speech recognition system (the MIT Summit system) with the Unisys discourse understanding system Pundit. Pundit is a broad-coverage language understanding system used in a variety of...

متن کامل

Pundit 2.0

This paper presents and demonstrates Pundit, a semantic annotation tool that combines powerful annotation functionalities covering comments, tagging, entities markup and linking, composition of rich semantic statements with private/public annotation sharing and retrieval via REST API. The adoption of a flexible data model, based on RDF and an extension of the Open Annotation model, allows, on o...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1986