arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.02635cs.CL
收藏

有效利用Transformer网络进行实体跟踪

Effective Use of Transformer Networks for Entity Tracking

The University of Texas at Austin(德克萨斯大学奥斯汀分校)

Aditya Gupta, Greg Durrett

摘要:

在过程语言中跟踪实体需要理解对实体的操作所引起的转换以及这些实体的交互。虽然GPT和BERT等基于自我注意力的预训练语言编码器已成功应用于一系列自然语言理解任务,但它们处理过程文本细微差别的能力仍未得到测试。在本文中,我们探讨了使用预训练的Transformer网络的实体跟踪任务的过程文本。首先,我们使用预先训练的Transformers测试了标准的轻量级预测方法,发现这些方法甚至不如简单的基线。我们表明,更强大的结果,可以通过重组的输入,以指导Transformer模型专注于一个特定的实体。其次,我们评估Transformer网络捕获过程动态的程度,调查合并实体和倾斜实体引用等因素。在两个不同的任务上,配方中的成分检测和科学过程中的QA,我们实现了最先进的结果,但我们的模型仍然主要关注浅层上下文线索,并且没有形成中间实体或过程状态的复杂表示。

英文摘要:

Tracking entities in procedural language requires understanding the transformations arising from actions on entities as well as those entities' interactions. While self-attention-based pre-trained language encoders like GPT and BERT have been successfully applied across a range of natural language understanding tasks, their ability to handle the nuances of procedural texts is still untested. In this paper, we explore the use of pre-trained transformer networks for entity tracking tasks in procedural text. First, we test standard lightweight approaches for prediction with pre-trained transformers, and find that these approaches underperform even simple baselines. We show that much stronger results can be attained by restructuring the input to guide the transformer model to focus on a particular entity. Second, we assess the degree to which transformer networks capture the process dynamics, investigating such factors as merged entities and oblique entity references. On two different tasks, ingredient detection in recipes and QA over scientific processes, we achieve state-of-the-art results, but our models still largely attend to shallow context clues and do not form complex representations of intermediate entity or process state.

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。

↑