Evaluation

Open-Domain Dialog Evaluation Using Follow-Ups Likelihood COLING 2022 PaCo: Preconditions Attributed to Commonsense Knowledge EMNLP 2022 Partial-input baselines show that NLI models can ignore context, but they don’t. NAACL 2022 Perceptual Quality Dimensions of Machine-Generated Text with a Focus on Machine Translation ACL 2022 Play the Shannon Game with Language Models: A Human-Free Approach to Summary Evaluation AAAI 2022 Possible Stories: Evaluating Situated Commonsense Reasoning under Multiple Possible Scenarios COLING 2022 Practical Evaluation of Adversarial Robustness via Adaptive Auto Attack CVPR 2022 Predicting Difficulty and Discrimination of Natural Language Questions ACL 2022 Predicting label distribution improves non-intrusive speech quality estimation Interspeech 2022 Pre-trained language models evaluating themselves - A comparative study ACL 2022 Probing Factually Grounded Content Transfer with Factual Ablation ACL 2022 Psycholinguistic Diagnosis of Language Models’ Commonsense Reasoning ACL 2022 PUMA: Performance Unchanged Model Augmentation for Training Data Removal AAAI 2022 Pythae: Unifying Generative Autoencoders in Python - A Benchmarking Use Case NeurIPS 2022 QAConv: Question Answering on Informative Conversations ACL 2022 QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarization NAACL 2022 QRelScore: Better Evaluating Generated Questions with Deeper Understanding of Context-aware Relevance EMNLP 2022 QSTS: A Question-Sensitive Text Similarity Measure for Question Generation COLING 2022 Qualitative Evaluation of Language Model Rescoring in Automatic Speech Recognition Interspeech 2022 Quantified Reproducibility Assessment of NLP Results ACL 2022 Quantifying Synthesis and Fusion and their Impact on Machine Translation NAACL 2022 Questioning the Validity of Summarization Datasets and Improving Their Factual Consistency EMNLP 2022 Re-Examining System-Level Correlations of Automatic Summarization Evaluation Metrics NAACL 2022 Relevance in Dialogue: Is Less More? An Empirical Comparison of Existing Metrics, and a Novel Simple Metric ACL 2022 Replicability under Near-Perfect Conditions – A Case-Study from Automatic Summarization ACL 2022