SNAP: parallel processing applied to AI

Moldovan, Dan; Lee, W.; Lin, C.; Chung, Minhwa

doi:10.1109/2.144394

Cited by 19 publications

(5 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to Moldovan et al (1992), Gulla (1996) and Dalianis (1997), this is the recommended and an e!ective way of obtaining a good compromise between natural language on the one hand and readability, focus and relevance on the other. The form of the pseudo-natural language statements constructed by the CQL system is, therefore, aimed at ease of understanding.…”

Section: Pseudo-natural Language Explainermentioning

confidence: 98%

Natural language querying of databases: an information extraction approach in the conceptual query language

Owei¹

2000

International Journal of Human-Computer Studies

View full text Add to dashboard Cite

Section: Pseudo-natural Language Explainermentioning

confidence: 98%

Natural language querying of databases: an information extraction approach in the conceptual query language

Owei¹

2000

International Journal of Human-Computer Studies

View full text Add to dashboard Cite

“…In the semantic network array processor (SNAP) (Moldovan, Lee, Lin and Chung, 1992), nodes of a knowledge graph represent concepts or their properties, while the interrelationships among nodes are represented by arcs. SNAP employs multiple processors to compute and construct multiple paths that correspond to a given knowledge.…”

Section: Related Research Related Research Related Research Related R...mentioning

confidence: 99%

A Paradigm For Natural Language Explanation Of Database Queries

Owei

Higa

1994

Journal of Database Management

View full text Add to dashboard Cite

“…The underlying ideas of the SNAP natural language processing system are : (1) memory based parsing , and (2) marker-passing on semantic networks [5] . In SNAP, parsing becomes a guided search over the knowledge base which stores linguistic information .…”

Section: Approachmentioning

confidence: 99%

Usc

Moldovan

Cha

Chung

et al. 1993

Proceedings of the 5th Conference on Message Understanding - MUC5 '93

View full text Add to dashboard Cite

INTRODUCTIO N Background The SNAP information extraction system has been developed as a part of a three-year SNAP projec t sponsored by the National Science Foundation. The main goal of the SNAP project is to build a massivel y parallel computer capable of fast and accurate natural language processing [5]. Throughout the project, a parallel computer was built in the Parallel Knowledge Processing Laboratory at USC, and various softwar e was developed to operate the machine [3]. The approach in designing SNAP was to find a knowledge representation and a reasoning paradigm useful for natural language processing which exhibits massive parallelism. We have selected marker-passing on semantic networks as a way to represent and process linguistic knowledge. The work for MUC-5 started at the end of January 1993. Prior to this we had implemented on SNA P a memory-based parsing system which was also used for MUC-4. Since the domain has been changed fro m MUC-4, we improved the dictionary with semantic tags necessary for EJV domain, developed a new templat e generation module, and constructed a new knowledge base including concept hierarchy and concept sequenc e patterns for parsing. Our group consisting of one faculty and five graduate students spent approximately 6 months to engineer a large system .

show abstract

SNAP: parallel processing applied to AI

Cited by 19 publications

References 4 publications

Natural language querying of databases: an information extraction approach in the conceptual query language

Natural language querying of databases: an information extraction approach in the conceptual query language

A Paradigm For Natural Language Explanation Of Database Queries

Usc

Contact Info

Product

Resources

About