Taking Advantage of BiLSTM Encoding to Handle Punctuation in Dependency Parsing: A Brief Idea
Matteo Grella
January 2018
 

In the context of the bidirectional-LSTMs neural parser (Kiperwasser and Goldberg, 2016), an idea is proposed to initialize the parsing state without punctuation-tokens but using them for the BiLSTM sentence encoding. The relevant information brought by the punctuation-tokens should be implicitly learned using the errors of the recurrent contributions only.
Format: [ pdf ]
Reference: lingbuzz/003802
(please use that when you cite this article)
Published in: http://vixra.org/pdf/1801.0041v1.pdf
keywords: dependency parsing, deep learning, syntax
Downloaded:212 times

 

[ edit this article | back to article list ]