No full text
Eprint already available on another site (E-prints, Working papers and Research blog)
BTPK-based learning: An Interpretable Method for Named Entity Recognition
Chen, Yulin; Yao, Zelai; Chi, Haixiao et al.


Full Text
No document available.

Send to


Keywords :
Computation and Language (cs.CL); Artificial Intelligence (cs.AI); FOS: Computer and information sciences
Abstract :
[en] Named entity recognition (NER) is an essential task in natural language processing, but the internal mechanism of most NER models is a black box for users. In some high-stake decision-making areas, improving the interpretability of an NER method is crucial but challenging. In this paper, based on the existing Deterministic Talmudic Public announcement logic (TPK) model, we propose a novel binary tree model (called BTPK) and apply it to two widely used Bi-RNNs to obtain BTPK-based interpretable ones. Then, we design a counterfactual verification module to verify the BTPK-based learning method. Experimental results on three public datasets show that the BTPK-based learning outperform two classical Bi-RNNs with self-attention, especially on small, simple data and relatively large, complex data. Moreover, the counterfactual verification demonstrates that the explanations provided by the BTPK-based learning method are reasonable and accurate in NER tasks. Besides, the logical reasoning based on BTPK shows how Bi-RNNs handle NER tasks, with different distance of public announcements on long and complex sequences.
Disciplines :
Computer science
Author, co-author :
Chen, Yulin
Yao, Zelai
Chi, Haixiao
Gabbay, Dov M. ;  University of Luxembourg > Faculty of Science, Technology and Communication (FSTC) > Computer Science and Communications Research Unit (CSC)
Yuan, Bo
Bentzen, Bruno
Liao, Beishui
Language :
Title :
BTPK-based learning: An Interpretable Method for Named Entity Recognition
Publication date :
Publisher :
Available on ORBilu :
since 30 January 2023


Number of views
18 (0 by Unilu)
Number of downloads
0 (0 by Unilu)


Similar publications

Contact ORBilu