Show newer

Private Meeting Summarization Without Performance Loss. (arXiv:2305.15894v1 [cs.CL]) 

CSS: A Large-scale Cross-schema Chinese Text-to-SQL Medical Dataset. (arXiv:2305.15891v1 [cs.CL]) 

LFTK: Handcrafted Features in Computational Linguistics. (arXiv:2305.15878v1 [cs.CL]) 

Linguistic Properties of Truthful Response. (arXiv:2305.15875v1 [cs.CL]) 

Jointprop: Joint Semi-supervised Learning for Entity and Relation Extraction with Heterogeneous Graph-based Propagation. (arXiv:2305.15872v1 [cs.CL]) 

Extracting Text Representations for Terms and Phrases in Technical Domains. (arXiv:2305.15867v1 [cs.CL]) 

Sequential Integrated Gradients: a simple but effective method for explaining language models. (arXiv:2305.15853v1 [cs.CL]) 

Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation. (arXiv:2305.15852v1 [cs.CL]) 

Bhasha-Abhijnaanam: Native-script and romanized Language Identification for 22 Indic languages. (arXiv:2305.15814v1 [cs.CL]) 

Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers. (arXiv:2305.15805v1 [cs.CL]) 

MERGE: Fast Private Text Generation. (arXiv:2305.15769v1 [cs.CL]) 

Svarah: Evaluating English ASR Systems on Indian Accents. (arXiv:2305.15760v1 [cs.CL]) 

Healing Unsafe Dialogue Responses with Weak Supervision Signals. (arXiv:2305.15757v1 [cs.CL]) 

UniTRec: A Unified Text-to-Text Transformer and Joint Contrastive Learning Framework for Text-based Recommendation. (arXiv:2305.15756v1 [cs.CL]) 

Multilingual Text-to-Speech Synthesis for Turkic Languages Using Transliteration. (arXiv:2305.15749v1 [eess.AS]) 

Learn to Not Link: Exploring NIL Prediction in Entity Linking. (arXiv:2305.15725v1 [cs.CL]) 

Comparative Study of Pre-Trained BERT Models for Code-Mixed Hindi-English Data. (arXiv:2305.15722v1 [cs.CL]) 

Towards Higher Pareto Frontier in Multilingual Machine Translation. (arXiv:2305.15718v1 [cs.CL]) 

The False Promise of Imitating Proprietary LLMs. (arXiv:2305.15717v1 [cs.CL]) 

Zero-shot Approach to Overcome Perturbation Sensitivity of Prompts. (arXiv:2305.15689v1 [cs.CL]) 

Show older
Qoto Mastodon

QOTO: Question Others to Teach Ourselves
An inclusive, Academic Freedom, instance
All cultures welcome.
Hate speech and harassment strictly forbidden.