Interacting Knowledge Sources, Inspection and Analysis: Case-studies on Biomedical text processing

Parsa Bagherzadeh, Sabine Bergler


Abstract
In this paper we investigate the recently proposed multi-input RIM for inspectability. This framework follows an encapsulation paradigm, where external knowledge sources are encoded as largely independent modules, enabling transparency for model inspection.
Anthology ID:
2021.blackboxnlp-1.35
Volume:
Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Editors:
Jasmijn Bastings, Yonatan Belinkov, Emmanuel Dupoux, Mario Giulianelli, Dieuwke Hupkes, Yuval Pinter, Hassan Sajjad
Venue:
BlackboxNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
447–456
Language:
URL:
https://aclanthology.org/2021.blackboxnlp-1.35
DOI:
10.18653/v1/2021.blackboxnlp-1.35
Bibkey:
Cite (ACL):
Parsa Bagherzadeh and Sabine Bergler. 2021. Interacting Knowledge Sources, Inspection and Analysis: Case-studies on Biomedical text processing. In Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, pages 447–456, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Interacting Knowledge Sources, Inspection and Analysis: Case-studies on Biomedical text processing (Bagherzadeh & Bergler, BlackboxNLP 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-2/2021.blackboxnlp-1.35.pdf