Towards Robustness of Text-to-SQL Models Against Natural and Realistic Adversarial Table Perturbation. (arXiv:2212.09994v1 [cs.CL])
Joint Speech Transcription and Translation: Pseudo-Labeling with Out-of-Distribution Data. (arXiv:2212.09982v1 [cs.CL])
On Improving Summarization Factual Consistency from Natural Language Feedback. (arXiv:2212.09968v1 [cs.CL])
BUMP: A Benchmark of Unfaithful Minimal Pairs for Meta-Evaluation of Faithfulness Metrics. (arXiv:2212.09955v1 [cs.CL])
Future Sight: Dynamic Story Generation with Large Pretrained Language Models. (arXiv:2212.09947v1 [cs.CL])
Dialog2API: Task-Oriented Dialogue with API Description and Example Programs. (arXiv:2212.09946v1 [cs.CL])
AnyTOD: A Programmable Task-Oriented Dialog System. (arXiv:2212.09939v1 [cs.CL])
Improving the Robustness of Summarization Models by Detecting and Removing Input Noise. (arXiv:2212.09928v1 [cs.CL])
Inverse Reinforcement Learning for Text Summarization. (arXiv:2212.09917v1 [cs.CL])
Tokenization Consistency Matters for Generative Models on Extractive NLP Tasks. (arXiv:2212.09912v1 [cs.CL])
Inducing Character-level Structure in Subword-based Language Models with Type-level Interchange Intervention Training. (arXiv:2212.09897v1 [cs.CL])
Improved Long-Form Spoken Language Translation with Large Language Models. (arXiv:2212.09895v1 [cs.CL])
Asking Clarification Questions for Code Generation in General-Purpose Programming Language. (arXiv:2212.09885v1 [cs.CL])
Unsigned Play by Milan Kundera? An Authorship Attribution Study. (arXiv:2212.09879v1 [cs.CL])
A Comparative Study on Textual Saliency of Styles from Eye Tracking, Annotations, and Language Models. (arXiv:2212.09873v1 [cs.CL])
Detecting Contradictory COVID-19 Drug Efficacy Claims from Biomedical Literature. (arXiv:2212.09867v1 [cs.CL])
Z-ICL: Zero-Shot In-Context Learning with Pseudo-Demonstrations. (arXiv:2212.09865v1 [cs.CL])
Synthetic Pre-Training Tasks for Neural Machine Translation. (arXiv:2212.09864v1 [cs.CL])
Continuous Semi-Supervised Nonnegative Matrix Factorization. (arXiv:2212.09858v1 [cs.CL])
MANTIS at TSAR-2022 Shared Task: Improved Unsupervised Lexical Simplification with Pretrained Encoders. (arXiv:2212.09855v1 [cs.CL])
All recent Computation and Language articles on arXiv.org for the Fediverse
Inspired by https://twitter.com/arxiv_cscl