Left-to-Right Dependency Parsing with Pointer Networks
@article{FernndezGonzlez2019LefttoRightDP, title={Left-to-Right Dependency Parsing with Pointer Networks}, author={Daniel Fern{\'a}ndez-Gonz{\'a}lez and Carlos G{\'o}mez-Rodr{\'i}guez}, journal={ArXiv}, year={2019}, volume={abs/1903.08445} }
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… CONTINUE READING
Supplemental Code
25 Citations
Distilling Neural Networks for Greener and Faster Dependency Parsing
- Computer Science
- IWPT 2020
- 2020
- 4
- PDF
References
SHOWING 1-10 OF 35 REFERENCES
Improving Transition-Based Dependency Parsing with Buffer Transitions
- Computer Science
- EMNLP-CoNLL
- 2012
- 8
- PDF
Stanford's Graph-based Neural Dependency Parser at the CoNLL 2017 Shared Task
- Computer Science
- CoNLL Shared Task
- 2017
- 162
- PDF
Neural Probabilistic Model for Non-projective MST Parsing
- Computer Science, Mathematics
- IJCNLP
- 2017
- 30
- PDF
Distilling an Ensemble of Greedy Dependency Parsers into One MST Parser
- Computer Science
- EMNLP
- 2016
- 59
- PDF