CLAILGMar 22, 2023

Open-source Frame Semantic Parsing

arXiv:2303.12788v14 citationsh-index: 6Has Code
Originality Synthesis-oriented
AI Analysis

This addresses the difficulty for end-users in applying advanced frame semantic parsing models in practice, though it is incremental as it builds on existing methods like T5.

The paper tackles the problem of making state-of-the-art frame semantic parsing models accessible to end-users by developing an open-source library called Frame Semantic Transformer, which achieves near state-of-the-art performance on FrameNet 1.7 with a focus on ease-of-use.

While the state-of-the-art for frame semantic parsing has progressed dramatically in recent years, it is still difficult for end-users to apply state-of-the-art models in practice. To address this, we present Frame Semantic Transformer, an open-source Python library which achieves near state-of-the-art performance on FrameNet 1.7, while focusing on ease-of-use. We use a T5 model fine-tuned on Propbank and FrameNet exemplars as a base, and improve performance by using FrameNet lexical units to provide hints to T5 at inference time. We enhance robustness to real-world data by using textual data augmentations during training.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes