ConceptX: A Framework for Latent Concept Analysis
Open Access
- 26 June 2023
- journal article
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 37 (13) , 16395-16397
Abstract
The opacity of deep neural networks remains a challenge in deploying solutions where explanation is as important as precision. We present ConceptX, a human-in-the-loop framework for interpreting and annotating latent representational space in pre-trained Language Models (pLMs). We use an unsupervised method to discover concepts learned in these models and enable a graphical interface for humans to generate explanations for the concepts. To facilitate the process, we provide auto-annotations of the concepts (based on traditional linguistic ontologies). Such annotations enable development of a linguistic resource that directly represents latent concepts learned within deep NLP models. These include not just traditional linguistic concepts, but also task-specific or sensitive concepts (words grouped based on gender or religious connotation) that helps the annotators to mark bias in the model. The framework consists of two parts (i) concept discovery and (ii) annotation platform.Keywords
All Related Versions
This publication has 3 references indexed in Scilit:
- Neuron-level Interpretation of Deep NLP Models: A SurveyTransactions of the Association for Computational Linguistics, 2022
- The What-If Tool: Interactive Probing of Machine Learning ModelsIEEE Transactions on Visualization and Computer Graphics, 2019
- Agglomerative clustering using the concept of mutual nearest neighbourhoodPattern Recognition, 1978