Context Compression for Auto-regressive Transformers with Sentinel Tokens. (arXiv:2310.08152v1 [cs.CL])
On the Relevance of Phoneme Duration Variability of Synthesized Training Data for Automatic Speech Recognition. (arXiv:2310.08132v1 [cs.CL])
Fine-grained Conversational Decoding via Isotropic and Proximal Search. (arXiv:2310.08130v1 [cs.CL])
Who Wrote it and Why? Prompting Large-Language Models for Authorship Verification. (arXiv:2310.08123v1 [cs.CL])
Voice Conversion for Stuttered Speech, Instruments, Unseen Languages and Textually Described Voices. (arXiv:2310.08104v1 [eess.AS])
QASiNa: Religious Domain Question Answering using Sirah Nabawiyah. (arXiv:2310.08102v1 [cs.CL])
Promptor: A Conversational and Autonomous Prompt Generation Agent for Intelligent Text Entry Techniques. (arXiv:2310.08101v1 [cs.CL])
ClimateNLP: Analyzing Public Sentiment Towards Climate Change Using Natural Language Processing. (arXiv:2310.08099v1 [cs.CL])
Low-Resource Clickbait Spoiling for Indonesian via Question Answering. (arXiv:2310.08085v1 [cs.CL])
To token or not to token: A Comparative Study of Text Representations for Cross-Lingual Transfer. (arXiv:2310.08078v1 [cs.CL])
Training Generative Question-Answering on Synthetic Data Obtained from an Instruct-tuned Mo. (arXiv:2310.08072v1 [cs.CL])
Rethinking Negative Pairs in Code Search. (arXiv:2310.08069v1 [cs.SE])
QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models. (arXiv:2310.08041v1 [cs.CL])
Exploring Large Language Models for Multi-Modal Out-of-Distribution Detection. (arXiv:2310.08027v1 [cs.CL])
Harnessing Large Language Models' Empathetic Response Generation Capabilities for Online Mental Health Counselling Support. (arXiv:2310.08017v1 [cs.CL])
Think, Act, and Ask: Open-World Interactive Personalized Robot Navigation. (arXiv:2310.07968v1 [cs.RO])
Clustering of Spell Variations for Proper Nouns Transliterated from the other languages. (arXiv:2310.07962v1 [cs.CL])
A New Approach Towards Autoformalization. (arXiv:2310.07957v1 [cs.CL])
D2 Pruning: Message Passing for Balancing Diversity and Difficulty in Data Pruning. (arXiv:2310.07931v1 [cs.LG])
Crosslingual Structural Priming and the Pre-Training Dynamics of Bilingual Language Models. (arXiv:2310.07929v1 [cs.CL])
All recent Computation and Language articles on arXiv.org for the Fediverse
Inspired by https://twitter.com/arxiv_cscl