Taking Advantage of BiLSTM Encoding to Handle Punctuation in Dependency Parsing: A Brief Idea
Year: 2018
Type: preprint
Abstract: 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.
Source: HAL
Author: Matteo Grella
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2782474005