# A Structured Span Selector

arXiv: https://arxiv.org/abs/2205.03977 · HTML: https://mlsanity.com/paper/2205.03977/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 38 references that are in the map.
- First posted on arXiv 8 May 2022.

## Builds on (most cited first, 19 of 19)

- [SpanBERT: Improving Pre-training by Representing and Predicting Spans](https://mlsanity.com/paper/1907.10529/) (2019)
- [End-to-end Neural Coreference Resolution](https://mlsanity.com/paper/1707.07045/) (2017)
- [Simple BERT Models for Relation Extraction and Semantic Role Labeling](https://mlsanity.com/paper/1904.05255/) (2019)
- [Higher-order Coreference Resolution with Coarse-to-fine Inference](https://mlsanity.com/paper/1804.05392/) (2018)
- [BERT for Coreference Resolution: Baselines and Analysis](https://mlsanity.com/paper/1908.09091/) (2019)
- [Coreference Resolution as Query-based Span Prediction](https://mlsanity.com/paper/1911.01746/) (2019)
- [An Annotated Dataset of Coreference in English Literature](https://mlsanity.com/paper/1912.01140/) (2019)
- [Revealing the Myth of Higher-Order Inference in Coreference Resolution](https://mlsanity.com/paper/2009.12013/) (2020)
- [Coreference Resolution without Span Representations](https://mlsanity.com/paper/2101.00434/) (2021)
- [Word-Level Coreference Resolution](https://mlsanity.com/paper/2109.04127/) (2021)
- [Jointly Predicting Predicates and Arguments in Neural Semantic Role Labeling](https://mlsanity.com/paper/1805.04787/) (2018)
- [Learning to Ignore: Long Document Coreference with Bounded Memory Neural Networks](https://mlsanity.com/paper/2010.02807/) (2020)
- [Syntactic Scaffolds for Semantic Structures](https://mlsanity.com/paper/1808.10485/) (2018)
- [Dependency or Span, End-to-End Uniform Semantic Role Labeling](https://mlsanity.com/paper/1901.05280/) (2019)
- [Neural Coreference Resolution with Deep Biaffine Attention by Joint Mention Detection and Mention Clustering](https://mlsanity.com/paper/1805.04893/) (2018)
- [A Span Selection Model for Semantic Role Labeling](https://mlsanity.com/paper/1810.02245/) (2018)
- [A Simple and Accurate Syntax-Agnostic Neural Model for Dependency-based Semantic Role Labeling](https://mlsanity.com/paper/1701.02593/) (2017)
- [Neural Mention Detection](https://mlsanity.com/paper/1907.12524/) (2019)
- [Partially-supervised Mention Detection](https://mlsanity.com/paper/1908.09507/) (2019)

## Built on by (most cited first, 3 of 3)

- [Autoregressive Structured Prediction with Language Models](https://mlsanity.com/paper/2210.14698/) (2022)
- [Linear-Time Modeling of Linguistic Structure: An Order-Theoretic Perspective](https://mlsanity.com/paper/2305.15057/) (2023)
- [Just Use XML: Revisiting Joint Translation and Label Projection](https://mlsanity.com/paper/2603.12021/) (2026)

## Abstract (arXiv)

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.