Real-world sentence boundary detection using multitask learning: A case study on French-Reference-Cited by-同舟云学术

Real-world sentence boundary detection using multitask learning: A case study on French

Published:2022-04-06 Issue: Volume: Page:1-21
ISSN:1351-3249
Container-title:Natural Language Engineering
language:en
Short-container-title:Nat. Lang. Eng.

Author:

Lim KyungTae^ORCID,Park Jungyeul^ORCID

Abstract

Abstract We propose a novel approach for sentence boundary detection in text datasets in which boundaries are not evident (e.g., sentence fragments). Although detecting sentence boundaries without punctuation marks has rarely been explored in written text, current real-world textual data suffer from widespread lack of proper start/stop signaling. Herein, we annotate a dataset with linguistic information, such as parts of speech and named entity labels, to boost the sentence boundary detection task. Via experiments, we obtained F1 scores up to 98.07% using the proposed multitask neural model, including a score of 89.41% for sentences completely lacking punctuation marks. We also present an ablation study and provide a detailed analysis to demonstrate the effectiveness of the proposed multitask learning method.

Publisher

Cambridge University Press (CUP)

Subject

Artificial Intelligence,Linguistics and Language,Language and Linguistics,Software

Reference37 articles.

1. Unsupervised Cross-lingual Representation Learning at Scale

2. Devlin, J. , Chang, M. , Lee, K. and Toutanova, K. (2018). BERT: Pre-training of deep bidirectional transformers for language understanding. CoRR, abs/1810.04805.

3. Evang, K. , Basile, V. , Chrupala, G. and Bos, J. (2013). Elephant: Sequence labeling for word and sentence segmentation. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, Seattle, Washington, USA. Association for Computational Linguistics, pp. 1422–1426.

4. Hashimoto, K. , Xiong, C. , Tsuruoka, Y. and Socher, R. (2016). A joint many-task model: Growing a neural network for multiple NLP tasks. CoRR, abs/1611.01587.

5. Neudecker, C. (2016). An open corpus for named entity recognition in historic newspapers. In Calzolari N., Choukri K., Declerck T., Goggi S., Grobelnik M., Maegaard B., Mariani J., Mazo H., Moreno A., Odijk J. and Piperidis S. (eds), Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016), Portorož, Slovenia. European Language Resources Association (ELRA), pp. 4348–4352.