# A Span Selection Model for Semantic Role Labeling

arXiv: https://arxiv.org/abs/1810.02245 · HTML: https://mlsanity.com/paper/1810.02245/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Oct 2018.

## Built on by (most cited first, 15 of 15)

- [Pushing the Limits of ChatGPT on NLP Tasks](https://mlsanity.com/paper/2306.09719/) (2023)
- [Semantic Role Labeling as Dependency Parsing: Exploring Latent Tree Structures Inside Arguments](https://mlsanity.com/paper/2110.06865/) (2021)
- [Demoting the Lead Bias in News Summarization via Alternating Adversarial Learning](https://mlsanity.com/paper/2105.14241/) (2021)
- [A Double-Graph Based Framework for Frame Semantic Parsing](https://mlsanity.com/paper/2206.09158/) (2022)
- [Conversational Semantic Role Labeling](https://mlsanity.com/paper/2104.04947/) (2021)
- [Syntax-Aware Graph-to-Graph Transformer for Semantic Role Labelling](https://mlsanity.com/paper/2104.07704/) (2021)
- [Constraining Linear-chain CRFs to Regular Languages](https://mlsanity.com/paper/2106.07306/) (2021)
- [WhyAct: Identifying Action Reasons in Lifestyle Vlogs](https://mlsanity.com/paper/2109.02747/) (2021)
- [An MRC Framework for Semantic Role Labeling](https://mlsanity.com/paper/2109.06660/) (2021)
- [A Structured Span Selector](https://mlsanity.com/paper/2205.03977/) (2022)
- [Argument Linking: A Survey and Forecast](https://mlsanity.com/paper/2107.08523/) (2021)
- [Sent2Span: Span Detection for PICO Extraction in the Biomedical Text without Span Annotations](https://mlsanity.com/paper/2109.02254/) (2021)
- [GrammarTagger: A Multilingual, Minimally-Supervised Grammar Profiler for Language Education](https://mlsanity.com/paper/2104.03190/) (2021)
- [SPOT: Knowledge-Enhanced Language Representations for Information Extraction](https://mlsanity.com/paper/2208.09625/) (2022)
- [Semantic Role Labeling of NomBank Partitives](https://mlsanity.com/paper/2412.14328/) (2024)

## Abstract (arXiv)

We present a simple and accurate span-based model for semantic role labeling (SRL). Our model directly takes into account all possible argument spans and scores them for each label. At decoding time, we greedily select higher scoring labeled spans. One advantage of our model is to allow us to design and use span-level features, that are difficult to use in token-based BIO tagging approaches. Experimental results demonstrate that our ensemble model achieves the state-of-the-art results, 87.4 F1 and 87.0 F1 on the CoNLL-2005 and 2012 datasets, respectively.