文章基本信息

标题：Interpretability Analysis for Named Entity Recognition to Understand System Predictions and How They Can Improve
本地全文：下载
作者：Oshin Agarwal ; Yinfei Yang ; Byron C. Wallace 等
期刊名称：Computational Linguistics
印刷版ISSN：0891-2017
电子版ISSN：1530-9312
出版年度：2021
卷号：47
期号：1
页码：117-140
DOI：10.1162/coli_a_00397
语种：English
出版社：MIT Press
摘要：AbstractNamed entity recognition systems achieve remarkable performance on domains such as English news. It is natural to ask: What are these models actually learning to achieve this? Are they merely memorizing the names themselves? Or are they capable of interpreting the text and inferring the correct entity type from the linguistic context? We examine these questions by contrasting the performance of several variants of architectures for named entity recognition, with some provided only representations of the context as features. We experiment with GloVe-based BiLSTM-CRF as well as BERT. We find that context does influence predictions, but the main factor driving high performance is learning the named tokens themselves. Furthermore, we find that BERT is not always better at recognizing predictive contexts compared to a BiLSTM-CRF model. We enlist human annotators to evaluate the feasibility of inferring entity types from context alone and find that humans are also mostly unable to infer entity types for the majority of examples on which the context-only system made errors. However, there is room for improvement: A system should be able to recognize any named entity in a predictive context correctly and our experiments indicate that current systems may be improved by such capability. Our human study also revealed that systems and humans do not always learn the same contextual clues, and context-only systems are sometimes correct even when humans fail to recognize the entity type from the context. Finally, we find that one issue contributing to model errors is the use of “entangled” representations that encode both contextual and local token information into a single vector, which can obscure clues. Our results suggest that designing models that explicitly operate over representations of local inputs and context, respectively, may in some cases improve performance. In light of these and related findings, we highlight directions for future work.