Fast and Accurate Non-Projective Dependency Tree Linearization
Xiang Yu, Simon Tannert, Ngoc Thang Vu, Jonas Kuhn
Generation Long Paper
Session 2B: Jul 6
(09:00-10:00 GMT)
Session 3A: Jul 6
(12:00-13:00 GMT)
Abstract:
We propose a graph-based method to tackle the dependency tree linearization task. We formulate the task as a Traveling Salesman Problem (TSP), and use a biaffine attention model to calculate the edge costs. We facilitate the decoding by solving the TSP for each subtree and combining the solution into a projective tree. We then design a transition system as post-processing, inspired by non-projective transition-based parsing, to obtain non-projective sentences. Our proposed method outperforms the state-of-the-art linearizer while being 10 times faster in training and decoding.
You can open the
pre-recorded video
in a separate window.
NOTE: The SlidesLive video may display a random order of the authors.
The correct author list is shown at the top of this webpage.