• English
  • Deutsch
  • Log In
    Password Login
    or
  • Research Outputs
  • Projects
  • Researchers
  • Institutes
  • Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Konferenzschrift
  4. Empirical Error Modeling Improves Robustness of Noisy Neural Sequence Labeling
 
  • Details
  • Full
Options
2021
Conference Paper
Titel

Empirical Error Modeling Improves Robustness of Noisy Neural Sequence Labeling

Abstract
Despite recent advances, standard sequence labeling systems often fail when processing noisy user-generated text or consuming the output of an Optical Character Recognition (OCR) process. In this paper, we improve the noise-aware training method by proposing an empirical error generation approach that employs a sequence-to-sequence model trained to perform translation from error-free to erroneous text. Using an OCR engine, we generated a large parallel text corpus for training and produced several real-world noisy sequence labeling benchmarks for evaluation. Moreover, to overcome the data sparsity problem that exacerbates in the case of imperfect textual input, we learned noisy language model-based embeddings. Our approach outperformed the baseline noise generation and error correction techniques on the erroneous sequence labeling data sets. To facilitate future research on robustness, we make our code, embeddings, and data conversion scripts publicly available.
Author(s)
Namysl, Marcin
Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme IAIS
Behnke, Sven
Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme IAIS
Köhler, Joachim
Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme IAIS
Hauptwerk
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021. Online resource
Konferenz
Association for Computational Linguistics (ACL Annual Meeting) 2021
International Joint Conference on Natural Language Processing (IJCNLP) 2021
DOI
10.18653/v1/2021.findings-acl.27
File(s)
N-643864.pdf (818.98 KB)
Language
English
google-scholar
Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme IAIS
  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Send Feedback
© 2022