Neural Modeling for Named Entities and Morphology (NEMO2)
Open Access
- 8 September 2021
- journal article
- research article
- Published by MIT Press in Transactions of the Association for Computational Linguistics
- Vol. 9, 909-928
Abstract
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 token- level 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.Keywords
All Related Versions
This publication has 25 references indexed in Scilit:
- Results of the WNUT2017 Shared Task on Novel and Emerging Entity Recognition2017
- Neural Morphological Analysis: Encoding-Decoding Canonical Segments2016
- Learning part-of-speech taggers with inter-annotator agreement loss2014
- Glove: Global Vectors for Word Representation2014
- Nested named entity recognition2009
- BioInfer: a corpus for information extraction in the biomedical domainBMC Bioinformatics, 2007
- ANERsys: An Arabic Named Entity Recognition System Based on Maximum Entropy2007
- Arabic tokenization, part-of-speech tagging and morphological disambiguation in one fell swoop2005
- A statistical information extraction system for TurkishNatural Language Engineering, 2003
- Introduction to the CoNLL-2003 shared task2003