arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.07682cs.CL
收藏

提升双仿射语义依存分析的辅助任务

Auxiliary Tasks to Boost Biaffine Semantic Dependency Parsing

Université Paris Cité(巴黎西岱大学);CNRS(法国国家科学研究中心)

Marie Candito

AI总结:

本文提出在双仿射语义依存分析中引入简单辅助任务以打破弧预测的独立性,在保留O(n^2)复杂度和并行架构的同时,于多个英文和法文数据集上实现了适度但系统的性能提升。

摘要:

Dozat和Manning(2017)的双仿射解析器被成功扩展至语义依存分析(SDP)(Dozat和Manning,2018)。鉴于在没有生成树约束的情况下,给定句子的所有弧都是彼此独立预测的(通过共享token表示取模),其在图上的表现高得令人惊讶。为了规避这种决策独立性,同时保留O(n^2)复杂度和高度可并行化的架构,我们提出使用简单的辅助任务,在弧之间引入某种形式的相互依赖。在SemEval 2015任务18(Oepen等人,2015)的三个英文无环数据集以及法语深层句法有环图(Ribeyre等人,2014)上的实验表明,在使用基于transformer的上下文表示的近最先进基线上,取得了适度但系统的性能提升。这提供了一种简单且稳健的方法来提升SDP性能。

英文摘要:

The biaffine parser of Dozat and Manning (2017) was successfully extended to semantic dependency parsing (SDP) (Dozat and Manning, 2018). Its performance on graphs is surprisingly high given that, without the constraint of producing a tree, all arcs for a given sentence are predicted independently from each other (modulo a shared representation of tokens). To circumvent such an independence of decision, while retaining the O(n^2) complexity and highly parallelizable architecture, we propose to use simple auxiliary tasks that introduce some form of interdependence between arcs. Experiments on the three English acyclic datasets of SemEval 2015 task 18 (Oepen et al., 2015), and on French deep syntactic cyclic graphs (Ribeyre et al., 2014) show modest but systematic performance gains on a near state-of-the-art baseline using transformer-based contextualized representations. This provides a simple and robust method to boost SDP performance.

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。

↑