arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.00563cs.CL
收藏

知识对一般NLU有帮助吗?实证研究

Does Knowledge Help General NLU? An Empirical Study

Microsoft Cognitive Services Research Group(微软认知服务研究组)

Ruochen Xu, Yuwei Fang, Chenguang Zhu, Michael Zeng

摘要:

它经常在以知识为中心的任务中观察到(例如,常识问答、关系分类),将诸如实体表示的外部知识集成到语言模型中可以帮助提供有用的信息以提高性能。然而,目前还不清楚这种好处是否可以扩展到一般的自然语言理解(NLU)任务。在这项工作中,我们实证研究的贡献,外部知识的测量端到端的性能语言模型与各种知识集成方法。我们发现,知识的引入可以显着提高某些任务的结果,而对其他任务没有不利影响。然后,我们使用互信息来反映知识带来的差异,并使用神经解释模型来揭示语言模型如何利用外部知识。我们的研究为从业者为NLP模型提供了有价值的见解和指导。

英文摘要:

It is often observed in knowledge-centric tasks (e.g., common sense question and answering, relation classification) that the integration of external knowledge such as entity representation into language models can help provide useful information to boost the performance. However, it is still unclear whether this benefit can extend to general natural language understanding (NLU) tasks. In this work, we empirically investigated the contribution of external knowledge by measuring the end-to-end performance of language models with various knowledge integration methods. We find that the introduction of knowledge can significantly improve the results on certain tasks while having no adverse effects on other tasks. We then employ mutual information to reflect the difference brought by knowledge and a neural interpretation model to reveal how a language model utilizes external knowledge. Our study provides valuable insights and guidance for practitioners to equip NLP models with knowledge.

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。

↑