Neural Modeling for Named Entities and Morphology (NEMO^2)

30 Jul 2020  ·  Dan Bareket, Reut Tsarfaty ·

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. read more

PDF Abstract

Datasets


Introduced in the Paper:

NEMO-Corpus
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Named Entity Recognition NEMO-Corpus (morph,test) LSTM-CharCNN-CRF morph hybrid F1 77.11 # 3
Named Entity Recognition NEMO-Corpus (token,test) LSTM-CharLSTM-CRF token-multi F1 77.75 # 2

Methods


No methods listed for this paper. Add relevant methods here