Reducing Discontinuous to Continuous Parsing with Pointer Network Reordering
This addresses the complexity and inefficiency in natural language processing for discontinuous parsing, offering a faster alternative while maintaining accuracy, though it is incremental as it builds on existing continuous parsers.
The paper tackled the problem of discontinuous constituent parsing by converting it into a continuous parsing task through token reordering, using a Pointer Network to generate arrangements and a bijective function for recovery, achieving accuracy comparable to state-of-the-art discontinuous parsers with significantly faster speed.
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.