Abstract
Dynamic oracle training has shown substantial improvements for dependency parsing in various settings, but has not been explored for constituent parsing. The present article introduces a dynamic oracle for transition-based constituent parsing. Experiments on the 9 languages of the SPMRL dataset show that a neural greedy parser with morphological features , trained with a dynamic oracle, leads to accuracies comparable with the best non-reranking and non-ensemble parsers.
Highlights
Constituent parsing often relies on search methods such as dynamic programming or beam search, because the search space of all possible predictions is prohibitively large
Dynamic oracles are widely used in dependency parsing and available for most standard transition systems (Goldberg and Nivre, 2013; Goldberg et al, 2014; Gomez-Rodrıguez et al, 2014; Straka et al, 2015), no dynamic oracle parsing model has yet been proposed for phrase structure grammars
We propose to rely on a neural network weighting function which uses a non-linear hidden layer to automatically capture interactions between variables, and embeds morphological features in a vector space, as is usual for words and other symbols (Collobert and Weston, 2008; Chen and Manning, 2014)
Summary
Constituent parsing often relies on search methods such as dynamic programming or beam search, because the search space of all possible predictions is prohibitively large. In NLP, dynamic oracles were first proposed to improve greedy dependency parsing training without involving additional computational costs at test time (Goldberg and Nivre, 2012; Goldberg and Nivre, 2013). Transition-based parsers usually rely on a static oracle, only welldefined for gold configurations, which transforms trees into sequences of gold actions. A solution is to train the parser to predict the best action given any configuration, by allowing it to explore a greater part of the search space at train time. We propose to rely on a neural network weighting function which uses a non-linear hidden layer to automatically capture interactions between variables, and embeds morphological features in a vector space, as is usual for words and other symbols (Collobert and Weston, 2008; Chen and Manning, 2014).
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have