Headed-Span-Based Projective Dependency Parsing
This work addresses dependency parsing for natural language processing, offering a novel approach that improves performance on standard benchmarks.
The paper tackles projective dependency parsing by introducing a method based on headed spans, representing trees as collections of these spans and using a dynamic programming algorithm for training and inference. It achieves state-of-the-art or competitive results on PTB, CTB, and UD datasets.
We propose a new method for projective dependency parsing based on headed spans. In a projective dependency tree, the largest subtree rooted at each word covers a contiguous sequence (i.e., a span) in the surface order. We call such a span marked by a root word \textit{headed span}. A projective dependency tree can be represented as a collection of headed spans. We decompose the score of a dependency tree into the scores of the headed spans and design a novel $O(n^3)$ dynamic programming algorithm to enable global training and exact inference. Our model achieves state-of-the-art or competitive results on PTB, CTB, and UD. Our code is publicly available at \url{https://github.com/sustcsonglin/span-based-dependency-parsing}.