4 and 7-bit Labeling for Projective and Non-Projective Dependency Trees
Submission Type: Regular Short Paper
Submission Track: Syntax, Parsing and their Applications
Keywords: parsing, dependency parsing, sequence labeling, parsing as sequence labeling, encoding
TL;DR: We define bounded encodings for dependency parsing as sequence labeling, which are more compact and empirically outperform previous encodings.
Abstract: 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.
Submission Number: 1554
Loading