Computer says "No": The Case Against Empathetic Conversational AI. (arXiv:2212.10983v2 [cs.CL] UPDATED)
Memory-efficient NLLB-200: Language-specific Expert Pruning of a Massively Multilingual Machine Translation Model. (arXiv:2212.09811v2 [cs.CL] UPDATED)
An Effective Employment of Contrastive Learning in Multi-label Text Classification. (arXiv:2212.00552v2 [cs.CL] UPDATED)
A Weakly-Supervised Streaming Multilingual Speech Model with Truly Zero-Shot Capability. (arXiv:2211.02499v2 [cs.CL] UPDATED)
A Chinese Spelling Check Framework Based on Reverse Contrastive Learning. (arXiv:2210.13823v2 [cs.CL] UPDATED)
Do Androids Laugh at Electric Sheep? Humor "Understanding" Benchmarks from The New Yorker Caption Contest. (arXiv:2209.06293v2 [cs.CL] UPDATED)
A Survey on Non-Autoregressive Generation for Neural Machine Translation and Beyond. (arXiv:2204.09269v2 [cs.CL] UPDATED)
Lost in the Middle: How Language Models Use Long Contexts. (arXiv:2307.03172v1 [cs.CL])
Focused Transformer: Contrastive Training for Context Scaling. (arXiv:2307.03170v1 [cs.CL])
Distilling Large Vision-Language Model with Out-of-Distribution Generalizability. (arXiv:2307.03135v1 [cs.CV])
T-MARS: Improving Visual Representations by Circumventing Text Feature Learning. (arXiv:2307.03132v1 [cs.CV])
BLEURT Has Universal Translations: An Analysis of Automatic Metrics by Minimum Risk Training. (arXiv:2307.03131v1 [cs.CL])
VisKoP: Visual Knowledge oriented Programming for Interactive Knowledge Base Question Answering. (arXiv:2307.03130v1 [cs.CL])
Extracting Multi-valued Relations from Language Models. (arXiv:2307.03122v1 [cs.CL])
KoRC: Knowledge oriented Reading Comprehension Benchmark for Deep Text Understanding. (arXiv:2307.03115v1 [cs.CL])
A Survey on Evaluation of Large Language Models. (arXiv:2307.03109v1 [cs.CL])
Efficient Domain Adaptation of Sentence Embeddings using Adapters. (arXiv:2307.03104v1 [cs.CL])
OpenDelta: A Plug-and-play Library for Parameter-efficient Adaptation of Pre-trained Models. (arXiv:2307.03084v1 [cs.LG])
DeepOnto: A Python Package for Ontology Engineering with Deep Learning. (arXiv:2307.03067v1 [cs.AI])
Parameter-Efficient Fine-Tuning of LLaMA for the Clinical Domain. (arXiv:2307.03042v1 [cs.CL])
All recent Computation and Language articles on arXiv.org for the Fediverse
Inspired by https://twitter.com/arxiv_cscl