A framework of a mechanical translation between Japanese and English by analogy principle
Proc. of the international NATO symposium on Artificial and human intelligence
Communications of the ACM - Special issue on parallelism
Semantic interpretation and the resolution of ambiguity
Semantic interpretation and the resolution of ambiguity
Natural language parsing systems
Information-based syntax and semantics: Vol. 1: fundamentals
Information-based syntax and semantics: Vol. 1: fundamentals
PARKA: parallel knowledge representation on the Connection Machine
PARKA: parallel knowledge representation on the Connection Machine
Integrating Marker Passing and Problem Solving: A Spreading Activation Approach to Improved Choice in Planning
Building Large Knowledge-Based Systems; Representation and Inference in the Cyc Project
Building Large Knowledge-Based Systems; Representation and Inference in the Cyc Project
Inside Case-Based Reasoning
Some Problems and Proposals for Knowledge Representation
Some Problems and Proposals for Knowledge Representation
A unified theory of inference for text understanding
A unified theory of inference for text understanding
Ambiguity resolution in the dmTrans Plus
EACL '89 Proceedings of the fourth conference on European chapter of the Association for Computational Linguistics
Inclusion, disjointness and choice: the logic of linguistic classification
ACL '91 Proceedings of the 29th annual meeting on Association for Computational Linguistics
Experiments and prospects of Example-Based Machine Translation
ACL '91 Proceedings of the 29th annual meeting on Association for Computational Linguistics
A transfer model using a typed feature structure rewriting system with inheritance
ACL '89 Proceedings of the 27th annual meeting on Association for Computational Linguistics
COLING '90 Proceedings of the 13th conference on Computational linguistics - Volume 3
Challenges of massive parallelism
IJCAI'93 Proceedings of the 13th international joint conference on Artifical intelligence - Volume 1
Hi-index | 0.00 |
This paper demonstrates the utility of the Semantic Network Array Processor (SNAP) as a massively parallel platform for high performance and large-scale natural language processing systems. SNAP is an experimental massively parallel machine which is dedicated to, but not limited to, the natural language processing using semantic networks. In designing the SNAP, we have investigated various natural language processing systems and theories to determine the scope of the hardware support and a set of micro-coded instructions to be provided. As a result, SNAP employs an extended marker-passing model and a dynamically modifiable network model. A set of primitive instructions is micro-coded to directly support a parallel marker-passing, bitoperations, numeric operations, network modifications, and other essential functions for natural language processing. This paper demonstrates the utility of SNAP for various paradigms of natural language processing. We have discovered that the SNAP provides milliseconds or microsectonds performance on several important applications such as the memory-based parsing and translation, classification-based parsing, and VLKB search. Also, we argue that there are numerous opportunities in the NLP community to take advantages of the computational power of the SNAP.