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.

翻译：基于框架语义的方法已被广泛用于语义解析任务并成为主流。然而，在不同上下文中消除目标词汇单位所引发的框架歧义仍具挑战性。预训练语言模型（PLMs）已被应用于语义解析，显著提升了神经解析器的准确性。但基于PLMs的方法倾向于偏向训练数据中呈现的搭配模式，导致结果不准确。本文的核心思路是设计一种机制，在联合使用PLMs与框架知识时，能最优地利用捕获的语义框架知识来消除歧义。我们提出了一种新颖的知识增强框架语义解析架构（KAF-SPA），通过在框架语义解析过程中将精确的框架知识融入PLMs来增强语义表示。具体而言，我们设计了一个基于记忆的知识提取模块（MKEM），用于选择精确的框架知识并在高维向量空间中构建连续模板。此外，我们设计了一个面向任务的知识探测模块（TKPM），采用混合提示（包括连续提示和离散提示）将所选知识融入PLMs，并适配PLMs以完成框架和论元识别任务。在两个公开的FrameNet数据集上的实验结果表明，我们的方法显著优于强基线（F1值提升超过+3%），在当前基准测试中达到了最先进水平。消融研究验证了KAF-SPA的有效性。