Left-to-Right Dependency Parsing with Pointer Networks
This work provides a more efficient and accurate dependency parser for natural language processing tasks, though it is incremental as it builds upon existing pointer network frameworks.
The authors tackled dependency parsing by introducing a left-to-right transition-based algorithm that reduces the transition sequence length from 2n-1 to n actions, resulting in a parser that runs twice as fast as the original while achieving state-of-the-art accuracy on the English PTB dataset (96.04% UAS, 94.43% LAS).
We propose a novel transition-based algorithm that straightforwardly parses sentences from left to right by building $n$ attachments, with $n$ being the length of the input sentence. Similarly to the recent stack-pointer parser by Ma et al. (2018), we use the pointer network framework that, given a word, can directly point to a position from the sentence. However, our left-to-right approach is simpler than the original top-down stack-pointer parser (not requiring a stack) and reduces transition sequence length in half, from 2$n$-1 actions to $n$. This results in a quadratic non-projective parser that runs twice as fast as the original while achieving the best accuracy to date on the English PTB dataset (96.04% UAS, 94.43% LAS) among fully-supervised single-model dependency parsers, and improves over the former top-down transition system in the majority of languages tested.