Confidence-Calibrated Ensemble Dense Phrase Retrieval. (arXiv:2306.15917v1 [cs.CL])
Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias. (arXiv:2306.15895v1 [cs.CL])
Symbol emergence as interpersonal cross-situational learning: the emergence of lexical knowledge with combinatoriality. (arXiv:2306.15837v1 [cs.CL])
MAT: Mixed-Strategy Game of Adversarial Training in Fine-tuning. (arXiv:2306.15826v1 [cs.CL])
Confidence-based Ensembles of End-to-End Speech Recognition Models. (arXiv:2306.15824v1 [eess.AS])
FLuRKA: Fast fused Low-Rank & Kernel Attention. (arXiv:2306.15799v1 [cs.LG])
Evaluating GPT-3.5 and GPT-4 on Grammatical Error Correction for Brazilian Portuguese. (arXiv:2306.15788v1 [cs.CL])
Next Steps for Human-Centered Generative AI: A Technical Perspective. (arXiv:2306.15774v1 [cs.HC])
Large Language Models as Annotators: Enhancing Generalization of NLP Models at Minimal Cost. (arXiv:2306.15766v1 [cs.CL])
Identity Construction in a Misogynist Incels Forum. (arXiv:2306.15745v1 [cs.CL])
Biomedical Entity Recognition by Detection and Matching. (arXiv:2306.15736v1 [cs.CL])
A Weakly Supervised Classifier and Dataset of White Supremacist Language. (arXiv:2306.15732v1 [cs.CL])
On the Universal Adversarial Perturbations for Efficient Data-free Adversarial Detection. (arXiv:2306.15705v1 [cs.CL])
Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale. (arXiv:2306.15687v1 [eess.AS])
Master-ASR: Achieving Multilingual Scalability and Low-Resource Adaptation in ASR with Modular Learning. (arXiv:2306.15686v1 [eess.AS])
Implementing contextual biasing in GPU decoder for online ASR. (arXiv:2306.15685v1 [eess.AS])
InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback. (arXiv:2306.14898v2 [cs.CL] UPDATED)
Kosmos-2: Grounding Multimodal Large Language Models to the World. (arXiv:2306.14824v2 [cs.CL] UPDATED)
Data-Driven Approach for Formality-Sensitive Machine Translation: Language-Specific Handling and Synthetic Data Generation. (arXiv:2306.14514v2 [cs.CL] UPDATED)
Cross-Language Speech Emotion Recognition Using Multimodal Dual Attention Transformers. (arXiv:2306.13804v2 [cs.CL] UPDATED)
All recent Computation and Language articles on arXiv.org for the Fediverse
Inspired by https://twitter.com/arxiv_cscl