4 and 7-bit Labeling for Projective and Non-Projective Dependency Trees
Use this link to cite
http://hdl.handle.net/2183/36571Collections
- OpenAIRE [353]
- GI-LYS - Congresos, conferencias, etc. [71]
Metadata
Show full item recordTitle
4 and 7-bit Labeling for Projective and Non-Projective Dependency TreesDate
2023-12Citation
Carlos Gómez-Rodríguez, Diego Roca, and David Vilares. 2023. 4 and 7-bit Labeling for Projective and Non-Projective Dependency Trees. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 6375–6384, Singapore. Association for Computational Linguistics.
Abstract
[Absctract]: We introduce an encoding for parsing as sequence labeling that can represent any projective dependency tree as a sequence of 4-bit labels, one per word. The bits in each word’s label represent (1) whether it is a right or left dependent, (2) whether it is the outermost (left/right) dependent of its parent, (3) whether it has any left children and (4) whether it has any right children. We show that this provides an injective mapping from trees to labels that can be encoded and decoded in linear time. We then define a 7-bit extension that represents an extra plane of arcs, extending the coverage to almost full non-projectivity (over 99.9% empirical arc coverage). Results on a set of diverse treebanks show that our 7-bit encoding obtains substantial accuracy gains over the previously best-performing sequence labeling encodings.
Keywords
Dependency parsing
Sequence labeling
Projective and non-projective dependency trees
Sequence labeling
Projective and non-projective dependency trees
Description
Singapore from Dec 6th to Dec 10th, 2023.
Editor version
Rights
Atribución 3.0 España