Confluent Preorder Parser as Finite State Automata

We present the Confluent Preorder Parser (CPP) in which syntactic parsing is achieved via a holistic transformation from the sentence representation to the desired parse tree representation. Simulation results show that CPP has achieved excellent generalization performance and is capable of handling erroneous sentences and resolving syntactic ambiguities. An analysis is presented which elucidates the operations of CPP as governed by a finite state automaton. The parsing is interpreted as a series of decision makings during the process. Based on this formalism, syntactic parsing and generalization by CPP can be explained in terms of state transitions.

[1]  Kanaan A. Faisal,et al.  Symbolic parsing via subsymbolic rules , 1992 .

[2]  Raymond L. Watrous,et al.  Induction of Finite-State Languages Using Second-Order Recurrent Networks , 1992, Neural Computation.

[3]  John Dinsmore,et al.  The symbolic and connectionist paradigms : closing the gap , 1992 .

[4]  Jordan B. Pollack,et al.  Massively Parallel Parsing: A Strongly Interactive Model of Natural Language Interpretation , 1988, Cogn. Sci..

[5]  David J. Chalmers,et al.  Syntactic Transformations on Distributed Representations , 1990 .

[6]  Stefan Wermter Hybrid Connectionist Natural Language Processing , 1994 .

[7]  Douglas S. Blank,et al.  Exploring the Symbolic/Subsymbolic Continuum: A case study of RAAM , 1992 .

[8]  Lonnie Chrisman,et al.  Learning Recursive Distributed Representations for Holistic Computation , 1991 .

[9]  C. Lee Giles,et al.  Learning and Extracting Finite State Automata with Second-Order Recurrent Neural Networks , 1992, Neural Computation.

[10]  Jordan B. Pollack,et al.  Recursive Distributed Representations , 1990, Artif. Intell..

[11]  Jeffrey D. Ullman,et al.  Introduction to Automata Theory, Languages and Computation , 1979 .

[12]  Risto Miikkulainen Subsymbolic Case-Role Analysis of Sentences with Embedded Clauses , 1993 .

[13]  Alexander H. Waibel,et al.  Incremental Parsing by Modular Recurrent Connectionist Networks , 1989, NIPS.

[14]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..