English

BTPK-based interpretable method for NER tasks based on Talmudic Public Announcement Logic

Computation and Language 2023-07-12 v2 Artificial Intelligence

Abstract

As one of the basic tasks in natural language processing (NLP), named entity recognition (NER) is an important basic tool for downstream tasks of NLP, such as information extraction, syntactic analysis, machine translation and so on. The internal operation logic of current name entity recognition model is black-box to the user, so the user has no basis to determine which name entity makes more sense. Therefore, a user-friendly explainable recognition process would be very useful for many people. In this paper, we propose a novel interpretable method, BTPK (Binary Talmudic Public Announcement Logic model), to help users understand the internal recognition logic of the name entity recognition tasks based on Talmudic Public Announcement Logic. BTPK model can also capture the semantic information in the input sentences, that is, the context dependency of the sentence. We observed the public announcement of BTPK presents the inner decision logic of BRNNs, and the explanations obtained from a BTPK model show us how BRNNs essentially handle NER tasks.

Keywords

Cite

@article{arxiv.2201.09523,
  title  = {BTPK-based interpretable method for NER tasks based on Talmudic Public Announcement Logic},
  author = {Yulin Chen and Beishui Liao and Bruno Bentzen and Bo Yuan and Zelai Yao and Haixiao Chi and Dov Gabbay},
  journal= {arXiv preprint arXiv:2201.09523},
  year   = {2023}
}

Comments

10 pages

R2 v1 2026-06-24T08:59:44.899Z