FastSpanNER: Speeding up SpanNER by Named Entity Head Prediction
Authors:
- 1 March 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 198-202
Abstract
Named Entity Recognition (NER) is one of the most fundamental tasks in natural language processing (NLP). Different from the widely-used sequence labeling framework in NER, span prediction based methods are more naturally suitable for the nested NER problem and have received a lot of attention recently. However, classifying the samples generated by traversing all sub-sequences is computational expensive during training and very ineffective at inference. In this paper, we propose the FastSpanNER approach to reduce the computation of both training and inferring. We introduce a task of Named Entity Head (NEH) prediction for each word in given sequence, and perform multi-task learning together with the task of span classification, which uses no more than half of the samples in SpanNER. In the inference phase, only the words predicted as NEHs are used to generate candidate spans for named entity classification. Experimental results on the four standard benchmark datasets (CoNLL2003, MSRA, CNERTA and GENIA) show that our FastSpanNER method not only greatly reduces the computation of training and inferring but also achieves better F1 scores compared with the SpanNER method.Keywords
This publication has 19 references indexed in Scilit:
- A Local Detection Approach for Named Entity Recognition and Mention Detection2017
- Named Entity Recognition with Bidirectional LSTM-CNNsTransactions of the Association for Computational Linguistics, 2016
- Joint Mention Extraction and Classification with Mention Hypergraphs2015
- A Convolutional Neural Network for Modelling Sentences2014
- Nested named entity recognition2009
- Identifying gene and protein mentions in text using conditional random fieldsBMC Bioinformatics, 2005
- GENIA corpus—a semantically annotated corpus for bio-textminingBioinformatics, 2003
- Introduction to the CoNLL-2003 shared task2003
- Early results for named entity recognition with conditional random fields, feature induction and web-enhanced lexicons2003
- Long Short-Term MemoryNeural Computation, 1997