Abstract
As the demand for explainable deep learning grows in the evaluation of language technologies, the value of a principled grounding for those explanations grows as well. Here we study the state-of-the-art in explanation for neural models for NLP tasks from the viewpoint of philosophy of science. We focus on recent evaluation work that finds brittleness in explanations obtained through attention mechanisms. We harness philosophical accounts of explanation to suggest broader conclusions from these studies. From this analysis, we assert the impossibility of causal explanations from attention layers over text data. We then introduce NLP researchers to contemporary philosophy of science theories that allow robust yet non-causal reasoning in explanation, giving computer scientists a vocabulary for future research.
Original language | English |
---|---|
Title of host publication | LREC 2020 - 12th International Conference on Language Resources and Evaluation, Conference Proceedings |
Editors | Nicoletta Calzolari, Frederic Bechet, Philippe Blache, Khalid Choukri, Christopher Cieri, Thierry Declerck, Sara Goggi, Hitoshi Isahara, Bente Maegaard, Joseph Mariani, Helene Mazo, Asuncion Moreno, Jan Odijk, Stelios Piperidis |
Pages | 1780-1790 |
Number of pages | 11 |
ISBN (Electronic) | 9791095546344 |
State | Published - 2020 |
Event | 12th International Conference on Language Resources and Evaluation, LREC 2020 - Marseille, France Duration: May 11 2020 → May 16 2020 |
Publication series
Name | LREC 2020 - 12th International Conference on Language Resources and Evaluation, Conference Proceedings |
---|
Conference
Conference | 12th International Conference on Language Resources and Evaluation, LREC 2020 |
---|---|
Country/Territory | France |
City | Marseille |
Period | 5/11/20 → 5/16/20 |
Bibliographical note
Publisher Copyright:© European Language Resources Association (ELRA), licensed under CC-BY-NC
Keywords
- Attention mechanisms
- Causal reasoning
- Explainability
- Philosophy of science
ASJC Scopus subject areas
- Language and Linguistics
- Education
- Library and Information Sciences
- Linguistics and Language