Hierarchical Pointer Net Parsing
This work addresses parsing inefficiencies for NLP researchers, though it appears incremental as it builds on existing pointer network methods.
The paper tackled the problem of transition-based top-down parsing with pointer networks having a sequential decoder that is not ideal for tree structures, and proposed hierarchical pointer network parsers, achieving new state-of-the-art results on dependency and discourse parsing benchmarks.
Transition-based top-down parsing with pointer networks has achieved state-of-the-art results in multiple parsing tasks, while having a linear time complexity. However, the decoder of these parsers has a sequential structure, which does not yield the most appropriate inductive bias for deriving tree structures. In this paper, we propose hierarchical pointer network parsers, and apply them to dependency and sentence-level discourse parsing tasks. Our results on standard benchmark datasets demonstrate the effectiveness of our approach, outperforming existing methods and setting a new state-of-the-art.