Abstract
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.
Abstract (translated)
过去几年中,框架语义解析的技术进展非常大,但对用户而言,在实践中应用最先进的模型仍然非常困难。为了解决这个问题,我们提出了Frame Semantic Transformer,一个开源的Python库,可以在FrameNet 1.7上实现最先进的性能,同时注重易用性。我们使用Propbank和FrameNet示例模型中的T5模型作为基础,并通过使用FrameNet词汇单元在推理时向T5提供提示来改进性能。在训练过程中,我们还使用文本数据增强来增强对真实数据的可靠性。
URL
https://arxiv.org/abs/2303.12788