We present two new datasets and a novel attention mechanism for Natural Language Inference (NLI). Existing neural NLI models, even though when trained on existing large datasets, do not capture the notion of entity and role well and often end up making mistakes such as "Peter signed a deal" can be inferred from "John signed a deal". The two datasets have been developed to mitigate such issues and make the systems better at understanding the notion of "entities" and "roles". After training the existing architectures on the new dataset we observe that the existing architectures does not perform well on one of the new benchmark. We then propose a modification to the "word-to-word" attention function which has been uniformly reused across several popular NLI architectures. The resulting architectures perform as well as their unmodified counterparts on the existing benchmarks and perform significantly well on the new benchmark for "roles" and "entities".
翻译:我们提出了两个新的数据集和一个关于自然语言推断的新关注机制(NLI ) 。 现有的神经国家LI模型,即使对现有大型数据集进行了培训,也不能很好地捕捉到实体和角色的概念,而且往往最终导致错误,如“Peter签署协议”可以从“John签署协议”中推断出来。 开发了两个数据集是为了缓解这些问题,使系统更好地了解“实体”和“作用”的概念。 在对新数据集的现有结构进行培训后,我们观察到,现有结构在新的基准之一上表现不佳。 我们然后提议修改“字对字”的注意功能,该功能已经在若干受欢迎的国家LI结构中统一地重新使用。 由此产生的结构与现有基准的对应结构一样运作,而且没有调整,在“作用”和“实体”的新基准上表现良好。