论文标题
指定实体和形态学的神经建模（NEMO^2）
Neural Modeling for Named Entities and Morphology (NEMO^2)
论文作者
论文摘要
命名实体识别（NER）是一项基本的NLP任务，通常以一系列令牌为单位。形态上丰富的语言（MRLS）对这种基本表述构成了挑战，因为指定实体的边界不一定与令牌边界相吻合，而是尊重形态学的界限。为了解决MRL中的NER，我们需要回答两个基本问题，即，要标记的基本单元是什么，以及如何在现实环境中检测和分类这些单元，即没有可用的黄金形态的地方。我们通过经验研究了这些问题，上面有一个新的NER基准测试，并采用平行的令牌和词素级别的注释，我们为现代希伯来语（一种形态上丰富且富有镜头的语言）开发了这些问题。 Our results show that explicitly modeling morphological boundaries leads to improved NER performance, and that a novel hybrid architecture, in which NER precedes and prunes morphological decomposition, greatly outperforms the standard pipeline, where morphological decomposition strictly precedes NER, setting a new performance bar for both Hebrew NER and Hebrew morphological decomposition tasks.
Named Entity Recognition (NER) is a fundamental NLP task, commonly formulated as classification over a sequence of tokens. Morphologically-Rich Languages (MRLs) pose a challenge to this basic formulation, as the boundaries of Named Entities do not necessarily coincide with token boundaries, rather, they respect morphological boundaries. To address NER in MRLs we then need to answer two fundamental questions, namely, what are the basic units to be labeled, and how can these units be detected and classified in realistic settings, i.e., where no gold morphology is available. We empirically investigate these questions on a novel NER benchmark, with parallel tokenlevel and morpheme-level NER annotations, which we develop for Modern Hebrew, a morphologically rich-and-ambiguous language. Our results show that explicitly modeling morphological boundaries leads to improved NER performance, and that a novel hybrid architecture, in which NER precedes and prunes morphological decomposition, greatly outperforms the standard pipeline, where morphological decomposition strictly precedes NER, setting a new performance bar for both Hebrew NER and Hebrew morphological decomposition tasks.
