Artificial Intelligence › Core AI ›

Interpretability

7318 directly classified papers

Papers per year

Papers

ALL Dolphins Are Intelligent and SOME Are Friendly: Probing BERT for Nouns’ Semantic Properties and their Prototypicality EMNLP 2021

ProSPer: Probing Human and Neural Network Language Model Understanding of Spatial Perspective EMNLP 2021

A howling success or a working sea? Testing what BERT knows about metaphors EMNLP 2021

Efficient Explanations from Empirical Explainers EMNLP 2021

Variation and generality in encoding of syntactic anomaly information in sentence embeddings EMNLP 2021

Enhancing Interpretable Clauses Semantically using Pretrained Word Representation EMNLP 2021

Analyzing BERT’s Knowledge of Hypernymy via Prompting EMNLP 2021

Screening Gender Transfer in Neural Machine Translation EMNLP 2021

How Familiar Does That Sound? Cross-Lingual Representational Similarity Analysis of Acoustic Word Embeddings EMNLP 2021

Interpretable Sequence Classification via Discrete Optimization AAAI 2021

Interpreting Multivariate Shapley Interactions in DNNs AAAI 2021

Bayes-TrEx: a Bayesian Sampling Approach to Model Transparency by Example AAAI 2021

A Unified Taylor Framework for Revisiting Attribution Methods AAAI 2021

Inverse Decision Modeling: Learning Interpretable Representations of Behavior ICML 2021

Perturbing Inputs for Fragile Interpretations in Deep Natural Language Processing EMNLP 2021

An Investigation of Language Model Interpretability via Sentence Editing EMNLP 2021

i-Algebra: Towards Interactive Interpretability of Deep Neural Networks AAAI 2021

Decision-Guided Weighted Automata Extraction from Recurrent Neural Networks AAAI 2021

Learning to Rationalize for Nonmonotonic Reasoning with Distant Supervision AAAI 2021

HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection AAAI 2021

Accurate and Interpretable Machine Learning for Transparent Pricing of Health Insurance Plans AAAI 2021

CLINE: Contrastive Learning with Semantic Negative Examples for Natural Language Understanding ACL 2021

More Identifiable yet Equally Performant Transformers for Text Classification ACL 2021

Scalable Partial Explainability in Neural Networks via Flexible Activation Functions (Student Abstract) AAAI 2021

Interpretable NLG for Task-oriented Dialogue Systems with Heterogeneous Rendering Machines AAAI 2021