# Knowledge-augmented Frame Semantic Parsing with Hybrid Prompt-tuning

arXiv: https://arxiv.org/abs/2303.14375 · HTML: https://mlsanity.com/paper/2303.14375/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 19 references that are in the map.
- First posted on arXiv 25 Mar 2023.

## Builds on (most cited first, 9 of 9)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [K-BERT: Enabling Language Representation with Knowledge Graph](https://mlsanity.com/paper/1909.07606/) (2019)
- [Frame-Semantic Parsing with Softmax-Margin Segmental RNNs and a Syntactic Scaffold](https://mlsanity.com/paper/1706.09528/) (2017)
- [Graph Convolutions over Constituent Trees for Syntax-Aware Semantic Role Labeling](https://mlsanity.com/paper/1909.09814/) (2019)
- [Open-Domain Frame Semantic Parsing Using Transformers](https://mlsanity.com/paper/2010.10998/) (2020)
- [A Double-Graph Based Framework for Frame Semantic Parsing](https://mlsanity.com/paper/2206.09158/) (2022)
- [Encoding Syntactic Constituency Paths for Frame-Semantic Parsing with Graph Convolutional Networks](https://mlsanity.com/paper/2011.13210/) (2020)

## Built on by (most cited first, 1 of 1)

- [Can LLMs Extract Frame-Semantic Arguments?](https://mlsanity.com/paper/2502.12516/) (2025)

## Abstract (arXiv)

Frame semantics-based approaches have been widely used in semantic parsing tasks and have become mainstream. It remains challenging to disambiguate frame representations evoked by target lexical units under different contexts. Pre-trained Language Models (PLMs) have been used in semantic parsing and significantly improve the accuracy of neural parsers. However, the PLMs-based approaches tend to favor collocated patterns presented in the training data, leading to inaccurate outcomes. The intuition here is to design a mechanism to optimally use knowledge captured in semantic frames in conjunction with PLMs to disambiguate frames. We propose a novel Knowledge-Augmented Frame Semantic Parsing Architecture (KAF-SPA) to enhance semantic representation by incorporating accurate frame knowledge into PLMs during frame semantic parsing. Specifically, a Memory-based Knowledge Extraction Module (MKEM) is devised to select accurate frame knowledge and construct the continuous templates in the high dimensional vector space. Moreover, we design a Task-oriented Knowledge Probing Module (TKPM) using hybrid prompts (in terms of continuous and discrete prompts) to incorporate the selected knowledge into the PLMs and adapt PLMs to the tasks of frame and argument identification. Experimental results on two public FrameNet datasets demonstrate that our method significantly outperforms strong baselines (by more than +3% in F1), achieving state-of-art results on the current benchmark. Ablation studies verify the effectiveness of KAF-SPA.