When Gradient Descent Meets Derivative-Free Optimization: A Match Made in Black-Box Scenario. (arXiv:2305.10013v1 [cs.CL])
AD-KD: Attribution-Driven Knowledge Distillation for Language Model Compression. (arXiv:2305.10010v1 [cs.CL])
EfficientSCI: Densely Connected Network with Space-time Factorization for Large-scale Video Snapshot Compressive Imaging. (arXiv:2305.10006v1 [cs.CV])
DinoSR: Self-Distillation and Online Clustering for Self-supervised Speech Representation Learning. (arXiv:2305.10005v1 [cs.CL])
Reprompting: Automated Chain-of-Thought Prompt Inference Through Gibbs Sampling. (arXiv:2305.09993v1 [cs.LG])
Dual Semantic Knowledge Composed Multimodal Dialog Systems. (arXiv:2305.09990v1 [cs.CL])
Smart Word Suggestions for Writing Assistance. (arXiv:2305.09975v1 [cs.CL])
CooK: Empowering General-Purpose Language Models with Modular and Collaborative Knowledge. (arXiv:2305.09955v1 [cs.CL])
"I'm fully who I am": Towards Centering Transgender and Non-Binary Voices to Measure Biases in Open Language Generation. (arXiv:2305.09941v1 [cs.CL])
Equivariant Few-Shot Learning from Pretrained Models. (arXiv:2305.09900v1 [cs.LG])
Balancing Lexical and Semantic Quality in Abstractive Summarization. (arXiv:2305.09898v1 [cs.CL])
Clustering-Aware Negative Sampling for Unsupervised Sentence Representation. (arXiv:2305.09892v1 [cs.CL])
Semantic Similarity Measure of Natural Language Text through Machine Learning and a Keyword-Aware Cross-Encoder-Ranking Summarizer -- A Case Study Using UCGIS GIS&T Body of Knowledge. (arXiv:2305.09877v1 [cs.CL])
The Jaseci Programming Paradigm and Runtime Stack: Building Scale-out Production Applications Easy and Fast. (arXiv:2305.09864v1 [cs.CL])
Explaining black box text modules in natural language with language models. (arXiv:2305.09863v1 [cs.AI])
Epsilon Sampling Rocks: Investigating Sampling Strategies for \\Minimum Bayes Risk Decoding for Machine Translation. (arXiv:2305.09860v1 [cs.CL])
Smaller Language Models are Better Black-box Machine-Generated Text Detectors. (arXiv:2305.09859v1 [cs.CL])
Knowledge Graph Completion Models are Few-shot Learners: An Empirical Study of Relation Labeling in E-commerce with LLMs. (arXiv:2305.09858v1 [cs.IR])
CoEdIT: Text Editing by Task-Specific Instruction Tuning. (arXiv:2305.09857v1 [cs.CL])
CPL-NoViD: Context-Aware Prompt-based Learning for Norm Violation Detection in Online Communities. (arXiv:2305.09846v1 [cs.CL])
All recent Computation and Language articles on arXiv.org for the Fediverse
Inspired by https://twitter.com/arxiv_cscl