Ambiguity resolution in the dmTrans Plus

Authors:
Hiroaki Kitano;Hideto Tomabechi;Lori Levin
Affiliations:
Carnegie Mellon University, Pittsburgh, PA;Carnegie Mellon University, Pittsburgh, PA;Carnegie Mellon University, Pittsburgh, PA
Venue:
EACL '89 Proceedings of the fourth conference on European chapter of the Association for Computational Linguistics
Year:
1989

Citing 7
Cited 4

Semantic interpretation and the resolution of ambiguity

Semantic interpretation and the resolution of ambiguity
Direct memory access parsing

Direct memory access parsing
Dynamic Memory: A Theory of Reminding and Learning in Computers and People

Dynamic Memory: A Theory of Reminding and Learning in Computers and People
Theory of Syntactic Recognition for Natural Languages

Theory of Syntactic Recognition for Natural Languages
A unified theory of inference for text understanding

A unified theory of inference for text understanding
The phrasal lexicon

TINLAP '75 Proceedings of the 1975 workshop on Theoretical issues in natural language processing
Application of the Direct Memory Access paradigm to natural language interfaces to knowledge-based systems

COLING '88 Proceedings of the 12th conference on Computational linguistics - Volume 2

Semantic Network Array Processor as a massively parallel computing platform for high performance and large-scale natural language processing

COLING '92 Proceedings of the 14th conference on Computational linguistics - Volume 2
Incremental sentence production with a parallel marker-passing algorithm

COLING '90 Proceedings of the 13th conference on Computational linguistics - Volume 2
Beyond PDP: the frequency modulation neural network architecture

IJCAI'89 Proceedings of the 11th international joint conference on Artificial intelligence - Volume 1
High performance natural language processing on semantic network array processor

IJCAI'91 Proceedings of the 12th international joint conference on Artificial intelligence - Volume 2

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a cost-based (or energy-based) model of disambiguation. When a sentence is ambiguous, a parse with the least cost is chosen from among multiple hypotheses. Each hypothesis is assigned a cost which is added when: (1) a new instance is created to satisfy reference success, (2) links between instances are created or removed to satisfy constraints on concept sequences, and (3) a concept node with insufficient priming is used for further processing. This method of ambiguity resolution is implemented in DMTRANS PLUS, which is a second generation bi-directional English/Japanese machine translation system based on a massively parallel spreading activation paradigm developed at the Center for Machine Translation at Carnegie Mellon University.