Interpretability

Just Add Functions: A Neural-Symbolic Language Model AAAI 2020 Justification-Based Reliability in Machine Learning AAAI 2020 KERMIT: Complementing Transformer Architectures with Encoders of Explicit Syntactic Interpretations EMNLP 2020 Language Model Transformers as Evaluators for Open-domain Dialogues COLING 2020 Language (Re)modelling: Towards Embodied Language Understanding ACL 2020 Large Scale Evaluation of Importance Maps in Automatic Speech Recognition Interspeech 2020 Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language? EMNLP 2020 Learning Code Changes by Exploiting Bidirectional Converting Deviation ACML 2020 Learning Differentiable Programs with Admissible Neural Heuristics NeurIPS 2020 Learning Explainable Linguistic Expressions with Neural Inductive Logic Programming for Sentence Classification EMNLP 2020 Learning from Demonstrations using Signal Temporal Logic CoRL 2020 Learning Global Transparent Models consistent with Local Contrastive Explanations NeurIPS 2020 Learning identifiable and interpretable latent models of high-dimensional neural activity using pi-VAE NeurIPS 2020 Learning Interpretable Models in the Property Specification Language IJCAI 2020 Learning Interpretable Models using Soft Integrity Constraints ACML 2020 Learning Interpretable Representations with Informative Entanglements IJCAI 2020 Learning Invariants through Soft Unification NeurIPS 2020 Learning Model with Error -- Exposing the Hidden Model of BAYHENN IJCAI 2020 Learning outside the Black-Box: The pursuit of interpretable models NeurIPS 2020 Learning Task-Driven Control Policies via Information Bottlenecks RSS 2020 Learning to Deceive with Attention-Based Explanations ACL 2020 Learning to Explain: Datasets and Models for Identifying Valid Reasoning Chains in Multihop Question-Answering EMNLP 2020 Learning to Faithfully Rationalize by Construction ACL 2020 Learning Variational Word Masks to Improve the Interpretability of Neural Text Classifiers EMNLP 2020 Learn to Combine Linguistic and Symbolic Information for Table-based Fact Verification COLING 2020