| Reference : BTPK-based learning: An Interpretable Method for Named Entity Recognition |
| E-prints/Working papers : Already available on another site | |||
| Engineering, computing & technology : Computer science | |||
| http://hdl.handle.net/10993/54262 | |||
| BTPK-based learning: An Interpretable Method for Named Entity Recognition | |
| English | |
| 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 [> >] | |
| 2022 | |
| arXiv | |
| No | |
| [en] Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI) ; FOS: Computer and information sciences ; FOS: Computer and information sciences | |
| [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. | |
| http://hdl.handle.net/10993/54262 | |
| 10.48550/ARXIV.2201.09523 | |
| https://arxiv.org/abs/2201.09523 | |
| https://arxiv.org/abs/2201.09523 |
There is no file associated with this reference.
All documents in ORBilu are protected by a user license.
