A Neural Lambda Calculus: Neurosymbolic AI meets the foundations of computing and functional programming. (arXiv:2304.09276v1 [cs.LG])
Token Imbalance Adaptation for Radiology Report Generation. (arXiv:2304.09185v1 [cs.CL])
A Comparative Study between Full-Parameter and LoRA-based Fine-Tuning on Chinese Instruction Data for Instruction Following Large Language Model. (arXiv:2304.08109v2 [cs.CL] UPDATED)
Chinese Open Instruction Generalist: A Preliminary Release. (arXiv:2304.07987v2 [cs.CL] UPDATED)
Neural Machine Translation For Low Resource Languages. (arXiv:2304.07869v2 [cs.CL] UPDATED)
Canvas: End-to-End Kernel Architecture Search in Neural Networks. (arXiv:2304.07741v2 [cs.LG] UPDATED)
Tractable Control for Autoregressive Language Generation. (arXiv:2304.07438v2 [cs.CL] UPDATED)
Quick Dense Retrievers Consume KALE: Post Training Kullback Leibler Alignment of Embeddings for Asymmetrical dual encoders. (arXiv:2304.01016v2 [cs.CL] UPDATED)
GrapeQA: GRaph Augmentation and Pruning to Enhance Question-Answering. (arXiv:2303.12320v2 [cs.CL] UPDATED)
XWikiGen: Cross-lingual Summarization for Encyclopedic Text Generation in Low Resource Languages. (arXiv:2303.12308v2 [cs.CL] UPDATED)
Feedback Effect in User Interaction with Intelligent Assistants: Delayed Engagement, Adaption and Drop-out. (arXiv:2303.10255v2 [cs.HC] UPDATED)
Large Language Models in the Workplace: A Case Study on Prompt Engineering for Job Type Classification. (arXiv:2303.07142v3 [cs.CL] UPDATED)
Reception Reader: Exploring Text Reuse in Early Modern British Publications. (arXiv:2302.04084v2 [cs.DL] UPDATED)
Erasure of Unaligned Attributes from Neural Representations. (arXiv:2302.02997v2 [cs.CL] UPDATED)
EXIF as Language: Learning Cross-Modal Associations Between Images and Camera Metadata. (arXiv:2301.04647v3 [cs.CV] UPDATED)
Topic Modelling of Swedish Newspaper Articles about Coronavirus: a Case Study using Latent Dirichlet Allocation Method. (arXiv:2301.03029v6 [cs.CL] UPDATED)
InferEM: Inferring the Speaker's Intention for Empathetic Dialogue Generation. (arXiv:2212.06373v4 [cs.CL] UPDATED)
Knowledge is Power: Understanding Causality Makes Legal judgment Prediction Models More Generalizable and Robust. (arXiv:2211.03046v2 [cs.CL] UPDATED)
Circling Back to Recurrent Models of Language. (arXiv:2211.01848v2 [cs.CL] UPDATED)
Variable Attention Masking for Configurable Transformer Transducer Speech Recognition. (arXiv:2211.01438v2 [eess.AS] UPDATED)
All recent Computation and Language articles on arXiv.org for the Fediverse
Inspired by https://twitter.com/arxiv_cscl