在基于Transformer的AMR解析中融入图信息
Incorporating Graph Information in Transformer-based AMR Parsing
AI总结：
本文提出LeakDistill模型，通过结构适配器将图信息融入Transformer编码器，结合词到节点对齐与自知识蒸馏，在不使用额外数据的情况下提升了AMR解析性能。
摘要：
抽象意义表示（AMR）是一种语义解析形式体系，旨在提供表示给定文本的语义图抽象。当前的方法基于自回归语言模型，如BART或T5，通过教师强制（Teacher Forcing）进行微调，从句子中获取AMR图的线性化版本。在本文中，我们提出了LeakDistill，一种模型和方法，探索对Transformer架构的修改，使用结构适配器将图信息显式地融入学习到的表示中，以提高AMR解析性能。我们的实验表明，通过在训练时将词到节点对齐用于将图结构信息嵌入编码器，即使不使用额外数据，我们也能通过自知识蒸馏获得最先进的AMR解析结果。我们在\footnote{http://www.github.com/sapienzanlp/LeakDistill}发布代码。
英文摘要：
Abstract Meaning Representation (AMR) is a Semantic Parsing formalism that aims at providing a semantic graph abstraction representing a given text. Current approaches are based on autoregressive language models such as BART or T5, fine-tuned through Teacher Forcing to obtain a linearized version of the AMR graph from a sentence. In this paper, we present LeakDistill, a model and method that explores a modification to the Transformer architecture, using structural adapters to explicitly incorporate graph information into the learned representations and improve AMR parsing performance. Our experiments show how, by employing word-to-node alignment to embed graph structural information into the encoder at training time, we can obtain state-of-the-art AMR parsing through self-knowledge distillation, even without the use of additional data. We release the code at \url{http://www.github.com/sapienzanlp/LeakDistill}.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
