# Open-Domain Frame Semantic Parsing Using Transformers

arXiv: https://arxiv.org/abs/2010.10998 · HTML: https://mlsanity.com/paper/2010.10998/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Oct 2020.

## Built on by (most cited first, 12 of 12)

- [A Double-Graph Based Framework for Frame Semantic Parsing](https://mlsanity.com/paper/2206.09158/) (2022)
- [An MRC Framework for Semantic Role Labeling](https://mlsanity.com/paper/2109.06660/) (2021)
- [Open-source Frame Semantic Parsing](https://mlsanity.com/paper/2303.12788/) (2023)
- [Query Your Model with Definitions in FrameNet: An Effective Method for Frame Semantic Role Labeling](https://mlsanity.com/paper/2212.02036/) (2022)
- [FRASE: Structured Representations for Generalizable SPARQL Query Generation](https://mlsanity.com/paper/2503.22144/) (2025)
- [Knowledge-augmented Frame Semantic Parsing with Hybrid Prompt-tuning](https://mlsanity.com/paper/2303.14375/) (2023)
- [Investigating Cost-Efficiency of LLM-Generated Training Data for Conversational Semantic Frame Analysis](https://mlsanity.com/paper/2410.06550/) (2024)
- [Enhancing Frame Detection with Retrieval Augmented Generation](https://mlsanity.com/paper/2502.12210/) (2025)
- [Beyond the Battlefield: Framing Analysis of Media Coverage in Conflict Reporting](https://mlsanity.com/paper/2506.10421/) (2025)
- [Evaluating the Impact of LLM-Assisted Annotation in a Perspectivized Setting: the Case of FrameNet Annotation](https://mlsanity.com/paper/2510.25904/) (2025)
- [The Multilingual FrameNet Corpus](https://mlsanity.com/paper/2608.23037/) (2026)
- [Syntax vs. Semantics: How Transformers Learn Deep Dependencies](https://mlsanity.com/paper/2608.26139/) (2026)

## Abstract (arXiv)

Frame semantic parsing is a complex problem which includes multiple underlying subtasks. Recent approaches have employed joint learning of subtasks (such as predicate and argument detection), and multi-task learning of related tasks (such as syntactic and semantic parsing). In this paper, we explore multi-task learning of all subtasks with transformer-based models. We show that a purely generative encoder-decoder architecture handily beats the previous state of the art in FrameNet 1.7 parsing, and that a mixed decoding multi-task approach achieves even better performance. Finally, we show that the multi-task model also outperforms recent state of the art systems for PropBank SRL parsing on the CoNLL 2012 benchmark.