A Structured Span Selector
This addresses the need for more effective span selection in NLP, offering a novel approach that could enhance performance in tasks requiring span-level decisions, though it appears incremental as it builds on existing span-based methods.
The paper tackles the problem of selecting text spans for NLP tasks like coreference resolution and semantic role labeling by proposing a grammar-based structured model that replaces heuristic greedy selection, resulting in empirical improvements on both tasks.
Many natural language processing tasks, e.g., coreference resolution and semantic role labeling, require selecting text spans and making decisions about them. A typical approach to such tasks is to score all possible spans and greedily select spans for task-specific downstream processing. This approach, however, does not incorporate any inductive bias about what sort of spans ought to be selected, e.g., that selected spans tend to be syntactic constituents. In this paper, we propose a novel grammar-based structured span selection model which learns to make use of the partial span-level annotation provided for such problems. Compared to previous approaches, our approach gets rid of the heuristic greedy span selection scheme, allowing us to model the downstream task on an optimal set of spans. We evaluate our model on two popular span prediction tasks: coreference resolution and semantic role labeling. We show empirical improvements on both.