Evaluation

Obtaining Faithful Interpretations from Compositional Neural Networks ACL 2020 On The Evaluation of Machine Translation Systems Trained With Back-Translation ACL 2020 On the Interplay Between Fine-tuning and Sentence-level Probing for Linguistic Knowledge in Pre-trained Transformers EMNLP 2020 On the Interplay Between Fine-tuning and Sentence-Level Probing for Linguistic Knowledge in Pre-Trained Transformers EMNLP 2020 Probing Linguistic Features of Sentence-Level Representations in Neural Relation Extraction ACL 2020 Relative Attributing Propagation: Interpreting the Comparative Contributions of Individual Units in Deep Neural Networks AAAI 2020 Revisiting Saliency Metrics: Farthest-Neighbor Area Under Curve CVPR 2020 SAM: The Sensitivity of Attribution Methods to Hyperparameters CVPR 2020 Sanity Checks for Saliency Metrics AAAI 2020 There and Back Again: Revisiting Backpropagation Saliency Methods CVPR 2020 Towards Holistic and Automatic Evaluation of Open-Domain Dialogue Generation ACL 2020 Towards Verifying Robustness of Neural Networks Against A Family of Semantic Perturbations CVPR 2020 TRENDNERT: A Benchmark for Trend and Downtrend Detection in a Scientific Domain AAAI 2020 WER we are and WER we think we are EMNLP 2020 What Do Position Embeddings Learn? An Empirical Study of Pre-Trained Language Model Positional Encoding EMNLP 2020 What Happens To BERT Embeddings During Fine-tuning? EMNLP 2020 A Benchmark for Interpretability Methods in Deep Neural Networks NeurIPS 2019 Analyzing Compositionality-Sensitivity of NLI Models AAAI 2019 Auditing Deep Learning processes through Kernel-based Explanatory Models EMNLP 2019 Certifying Geometric Robustness of Neural Networks NeurIPS 2019 Cold Case: The Lost MNIST Digits NeurIPS 2019 Demystifying Black-box Models with Symbolic Metamodels NeurIPS 2019 Detecting Overfitting of Deep Generative Networks via Latent Recovery CVPR 2019 Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study ACL 2019 Do You Know That Florence Is Packed with Visitors? Evaluating State-of-the-art Models of Speaker Commitment ACL 2019