Enriched In-Order Linearization for Faster Sequence-to-Sequence Constituent Parsing
This work addresses parsing efficiency and accuracy for NLP researchers, presenting an incremental improvement over existing methods.
The paper tackled the problem of sequence-to-sequence constituent parsing by proposing an enriched in-order linearization, achieving the best accuracy to date on the English PTB dataset among fully-supervised single-model parsers and matching state-of-the-art transition-based parsers in speed.
Sequence-to-sequence constituent parsing requires a linearization to represent trees as sequences. Top-down tree linearizations, which can be based on brackets or shift-reduce actions, have achieved the best accuracy to date. In this paper, we show that these results can be improved by using an in-order linearization instead. Based on this observation, we implement an enriched in-order shift-reduce linearization inspired by Vinyals et al. (2015)'s approach, achieving the best accuracy to date on the English PTB dataset among fully-supervised single-model sequence-to-sequence constituent parsers. Finally, we apply deterministic attention mechanisms to match the speed of state-of-the-art transition-based parsers, thus showing that sequence-to-sequence models can match them, not only in accuracy, but also in speed.