Distributed Representations, Simple Recurrent Networks, And Grammatical Structure
Machine Learning - Connectionist approaches to language learning
Description-based parsing in a connectionist network
Description-based parsing in a connectionist network
Neural Networks for Pattern Recognition
Neural Networks for Pattern Recognition
Incremental Syntactic Parsing of Natural Language Corpora with Simple Synchrony Networks
IEEE Transactions on Knowledge and Data Engineering
Head-driven statistical models for natural language parsing
Head-driven statistical models for natural language parsing
Building a large annotated corpus of English: the penn treebank
Computational Linguistics - Special issue on using large corpora: II
A connectionist architecture for learning to parse
COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 1
| Hi-index | 0.00 |
Simple Synchrony Networks (SSNs) have previously been shown to be a viable alternative method for syntactic parsing. Here we use an SSN to estimate the parameters of a probabilistic parsing model, and compare this parser's performance against a standard statistical parsing method, a Probabilistic Context Free Grammar. We focus these experiments on demonstrating one of the main advantages of SSNs, handling sparse data. We use smaller datasets than are typically used with statistical methods, resulting in the PCFG finding parses for only half of the test sentences, while the SSN parser finds parses for all sentences. Even on the PCFG's parsed half, the SSN parser performs better than the PCFG.