A Structured Span Selector

Anonymous

Paper Link: https://openreview.net/forum?id=V7hpFD65zL

Paper Type: Long paper (up to eight pages of content + unlimited references and appendices)

Abstract:

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; and show improvements on both.

Presentation Mode: This paper will be presented in person in Seattle

Copyright Consent Signature (type Name Or NA If Not Transferrable): Tianyu Liu

Copyright Consent Name And Address: ETH Zurich, Zurich, Switzerland