arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.04700cs.CLcs.LG
收藏

增加NLP数据以对抗NLI任务的注释伪影

Augmenting NLP data to counter Annotation Artifacts for NLI Tasks

Armaan Singh Bhullar

摘要:

在本文中,我们探讨了注释伪影-这种现象,其中大型预训练的NLP模型在基准数据集上实现了高性能,但实际上并没有“解决”底层任务,而是依赖于一些数据集伪影(在训练,验证和测试集上相同)来找出正确的答案。我们在著名的自然语言推理任务中探索了这一现象,首先使用对比和对抗性示例来理解模型性能的局限性,并展示了注释工件(注释器构建训练数据的方式)产生的偏见之一。然后,我们提出了一个数据增强技术来解决这个偏差,并衡量其有效性。

英文摘要:

In this paper, we explore Annotation Artifacts - the phenomena wherein large pre-trained NLP models achieve high performance on benchmark datasets but do not actually "solve" the underlying task and instead rely on some dataset artifacts (same across train, validation, and test sets) to figure out the right answer. We explore this phenomenon on the well-known Natural Language Inference task by first using contrast and adversarial examples to understand limitations to the model's performance and show one of the biases arising from annotation artifacts (the way training data was constructed by the annotators). We then propose a data augmentation technique to fix this bias and measure its effectiveness.

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。

↑