arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2109.04726cs.CLcs.IR
收藏

AutoTriggER:基于辅助触发词提取的标签高效且鲁棒的命名实体识别

AutoTriggER: Label-Efficient and Robust Named Entity Recognition with Auxiliary Trigger Extraction

University of Southern California(南加州大学);Information Science Institute, University of Southern California(南加州大学信息科学研究所);University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校)

Dong-Ho Lee, Ravi Kiran Selvam, Sheikh Muhammad Sarwar, Bill Yuchen Lin, Fred Morstatter, Jay Pujara, Elizabeth Boschee, James Allan, Xiang Ren

AI总结:

本文提出两阶段框架AutoTriggER,通过自动生成和利用“实体触发词”辅助命名实体识别,结合事后解释和嵌入插值技术增强模型先验知识,在三个数据集上表现出强标签效率并平均比RoBERTa-CRF基线高近0.5个F1点。

摘要:

命名实体识别(NER)的深度神经模型通过利用远程监督和解释等辅助信息,在克服标签稀缺和泛化到未见实体方面取得了令人瞩目的成果。然而,获取这些额外信息的成本通常是难以承受的。在本文中,我们提出了一个新颖的两阶段框架(AutoTriggER),通过自动生成和利用“实体触发词”来提高NER性能,这些触发词是文本中人类可读的线索,有助于引导模型做出更好的决策。我们的框架利用事后解释生成rationales,并使用嵌入插值技术增强模型的先验知识。这种方法使模型能够利用触发词推断实体边界和类型,而不是仅仅记忆实体词本身。通过在三个经过充分研究的NER数据集上的实验,AutoTriggER表现出强大的标签效率,能够泛化到未见实体,并且平均比RoBERTa-CRF基线高出近0.5个F1点。

英文摘要:

Deep neural models for named entity recognition (NER) have shown impressive results in overcoming label scarcity and generalizing to unseen entities by leveraging distant supervision and auxiliary information such as explanations. However, the costs of acquiring such additional information are generally prohibitive. In this paper, we present a novel two-stage framework (AutoTriggER) to improve NER performance by automatically generating and leveraging ``entity triggers'' which are human-readable cues in the text that help guide the model to make better decisions. Our framework leverages post-hoc explanation to generate rationales and strengthens a model's prior knowledge using an embedding interpolation technique. This approach allows models to exploit triggers to infer entity boundaries and types instead of solely memorizing the entity words themselves. Through experiments on three well-studied NER datasets, AutoTriggER shows strong label-efficiency, is capable of generalizing to unseen entities, and outperforms the RoBERTa-CRF baseline by nearly 0.5 F1 points on average.

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。

↑