Towards Realistic Single-Task Continuous Learning Research for NER. (arXiv:2110.14694v1 [cs.CL])

There is an increasing interest in continuous learning (CL), as data privacy
is becoming a priority for real-world machine learning applications. Meanwhile,
there is still a lack of academic NLP benchmarks that are applicable for
realistic CL settings, which is a major challenge for the advancement of the
field. In this paper we discuss some of the unrealistic data characteristics of
public datasets, study the challenges of realistic single-task continuous
learning as well as the effectiveness of data rehearsal as a way to mitigate
accuracy loss. We construct a CL NER dataset from an existing publicly
available dataset and release it along with the code to the research community.



Related post