Attention is not not explanation

Sarah Wiegreffe, Yuval Pinter

نتاج البحث: فصل من :كتاب / تقرير / مؤتمرمنشور من مؤتمرمراجعة النظراء

ملخص

Attention mechanisms play a central role in NLP systems, especially within recurrent neural network (RNN) models. Recently, there has been increasing interest in whether or not the intermediate representations offered by these modules may be used to explain the reasoning for a model's prediction, and consequently reach insights regarding the model's decision-making process. A recent paper claims that 'Attention is not Explanation' (Jain and Wallace, 2019). We challenge many of the assumptions underlying this work, arguing that such a claim depends on one's definition of explanation, and that testing it needs to take into account all elements of the model. We propose four alternative tests to determine when/whether attention can be used as explanation: a simple uniform-weights baseline; a variance calibration based on multiple random seed runs; a diagnostic framework using frozen weights from pretrained models; and an end-to-end adversarial attention training protocol. Each allows for meaningful interpretation of attention mechanisms in RNN models. We show that even when reliable adversarial distributions can be found, they don't perform well on the simple diagnostic, indicating that prior work does not disprove the usefulness of attention mechanisms for explainability.

اللغة الأصليةإنجليزيّة أمريكيّة
عنوان منشور المضيفEMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference
الصفحات11-20
عدد الصفحات10
رقم المعيار الدولي للكتب (الإلكتروني)9781950737901
حالة النشرنُشِر - 2019
منشور خارجيًانعم
الحدث2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019 - Hong Kong, الصين
المدة: ٣ نوفمبر ٢٠١٩٧ نوفمبر ٢٠١٩

سلسلة المنشورات

الاسمEMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference

!!Conference

!!Conference2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019
الدولة/الإقليمالصين
المدينةHong Kong
المدة٣/١١/١٩٧/١١/١٩

All Science Journal Classification (ASJC) codes

  • !!Computational Theory and Mathematics
  • !!Computer Science Applications
  • !!Information Systems

بصمة

أدرس بدقة موضوعات البحث “Attention is not not explanation'. فهما يشكلان معًا بصمة فريدة.

قم بذكر هذا