Learning to Generalize for Cross-domain QA. (arXiv:2305.08208v1 [cs.CL])
A Cognitive Stimulation Dialogue System with Multi-source Knowledge Fusion for Elders with Cognitive Impairment. (arXiv:2305.08200v1 [cs.CL])
Learning to Simulate Natural Language Feedback for Interactive Semantic Parsing. (arXiv:2305.08195v1 [cs.CL])
CroSentiNews 2.0: A Sentence-Level News Sentiment Corpus. (arXiv:2305.08187v1 [cs.CL])
Croatian Film Review Dataset (Cro-FiReDa): A Sentiment Annotated Dataset of Film Reviews. (arXiv:2305.08173v1 [cs.CL])
STORYWARS: A Dataset and Instruction Tuning Baselines for Collaborative Story Understanding and Generation. (arXiv:2305.08152v1 [cs.CL])
ParaLS: Lexical Substitution via Pretrained Paraphraser. (arXiv:2305.08146v1 [cs.CL])
Distinguish Before Answer: Generating Contrastive Explanation as Knowledge for Commonsense Question Answering. (arXiv:2305.08135v1 [cs.CL])
Towards Understanding and Improving Knowledge Distillation for Neural Machine Translation. (arXiv:2305.08096v1 [cs.CL])
Make Prompt-based Black-Box Tuning Colorful: Boosting Model Generalization from Three Orthogonal Perspectives. (arXiv:2305.08088v1 [cs.CL])
Improving End-to-End SLU performance with Prosodic Attention and Distillation. (arXiv:2305.08067v1 [cs.CL])
Semantic-aware Dynamic Retrospective-Prospective Reasoning for Event-level Video Question Answering. (arXiv:2305.08059v1 [cs.CV])
ProKnow: Process Knowledge for Safety Constrained and Explainable Question Generation for Mental Health Diagnostic Assistance. (arXiv:2305.08010v1 [cs.CL])
Beyond the Safeguards: Exploring the Security Risks of ChatGPT. (arXiv:2305.08005v1 [cs.CR])
Multilingual Previously Fact-Checked Claim Retrieval. (arXiv:2305.07991v1 [cs.CL])
Self-Supervised Sentence Compression for Meeting Summarization. (arXiv:2305.07988v1 [cs.CL])
SCENE: Self-Labeled Counterfactuals for Extrapolating to Negative Examples. (arXiv:2305.07984v1 [cs.CL])
Zero-shot Faithful Factual Error Correction. (arXiv:2305.07982v1 [cs.CL])
Trillion Dollar Words: A New Financial Dataset, Task & Market Analysis. (arXiv:2305.07972v1 [cs.CL])
GPT-Sentinel: Distinguishing Human and ChatGPT Generated Content. (arXiv:2305.07969v1 [cs.CL])
All recent Computation and Language articles on arXiv.org for the Fediverse
Inspired by https://twitter.com/arxiv_cscl