Reducing Discontinuous to Continuous Parsing with Pointer Network Reordering
Daniel Fernández‐González, Carlos Gómez‐Rodríguez · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · 2021
Discontinuous constituent parsers have always lagged behind continuous approaches in terms of accuracy and speed, as the presence of constituents with discontinuous yield introduces extra complexity to the task.However, a discontinuous tree can be converted into a continuous variant by reordering tokens.Based on that, we propose to reduce discontinuous parsing to a continuous problem, which can then be directly solved by any off-the-shelf continuous parser.To that end, we develop a Pointer Network capable of accurately generating the continuous token arrangement for a given input sentence and define a bijective function to recover the original order.Experiments on the main benchmarks with two continuous parsers prove that our approach is on par in accuracy with purely discontinuous state-of-the-art algorithms, but considerably faster.