NER-MQMRC：命名实体识别的多问题机器阅读理解
NER-MQMRC: Formulating Named Entity Recognition as Multi Question Machine Reading Comprehension
摘要：
NER传统上被制定为序列标记任务。然而，最近的趋势是将NER视为机器阅读理解任务（Wang等人，2020; Mengge等人，2020），其中实体名称（或其他信息）被认为是问题，文本作为上下文，并且文本中的实体值作为答案片段。这些作品认为MRC基于一个单一的问题（实体）的时间。我们建议将NER作为一个多问题MRC任务，其中多个问题（每个实体一个问题）被认为是在同一时间为一个单一的文本。我们提出了一种新的基于BERT的多问题MRC（NER-MQMRC）架构，这个配方。NER-MQMRC架构将所有实体视为BERT的输入，用于学习具有自我注意力的令牌嵌入，并利用基于BERT的实体表示来进一步改进NER任务的这些令牌嵌入。对三个NER数据集的评估表明，与基于NER-SQMRC框架的模型相比，我们提出的架构通过在单次通过中将所有实体考虑在一起，平均训练速度快2.5倍，推理速度快2.3倍。此外，我们表明，与基于单个问题的MRC（NER-SQMRC）相比，我们的模型性能不会降低（Devlin等人，2019年）导致AE-Pub，Ecc 5 PT和Twitter数据集的F1分别增长+0.41%，+0.32%和+0.27%。我们提出这种架构主要是为了解决大规模的电子商务属性（或实体）提取非结构化文本的幅度为50 k+属性上提取一个可扩展的生产环境具有高性能和优化的训练和推理运行时。
英文摘要：
NER has been traditionally formulated as a sequence labeling task. However, there has been recent trend in posing NER as a machine reading comprehension task (Wang et al., 2020; Mengge et al., 2020), where entity name (or other information) is considered as a question, text as the context and entity value in text as answer snippet. These works consider MRC based on a single question (entity) at a time. We propose posing NER as a multi-question MRC task, where multiple questions (one question per entity) are considered at the same time for a single text. We propose a novel BERT-based multi-question MRC (NER-MQMRC) architecture for this formulation. NER-MQMRC architecture considers all entities as input to BERT for learning token embeddings with self-attention and leverages BERT-based entity representation for further improving these token embeddings for NER task. Evaluation on three NER datasets show that our proposed architecture leads to average 2.5 times faster training and 2.3 times faster inference as compared to NER-SQMRC framework based models by considering all entities together in a single pass. Further, we show that our model performance does not degrade compared to single-question based MRC (NER-SQMRC) (Devlin et al., 2019) leading to F1 gain of +0.41%, +0.32% and +0.27% for AE-Pub, Ecommerce5PT and Twitter datasets respectively. We propose this architecture primarily to solve large scale e-commerce attribute (or entity) extraction from unstructured text of a magnitude of 50k+ attributes to be extracted on a scalable production environment with high performance and optimised training and inference runtimes.
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。
