Show newer
arXiv - CSCL

CHAMPAGNE: Learning Real-world Conversation from Large-Scale Web Videos. (arXiv:2303.09713v2 [cs.CL] UPDATED) 

arxiv.org/abs/2303.09713

0
arXiv - CSCL

Text-only domain adaptation for end-to-end ASR using integrated text-to-mel-spectrogram generator. (arXiv:2302.14036v2 [eess.AS] UPDATED) 

arxiv.org/abs/2302.14036

0
arXiv - CSCL

Editing Language Model-based Knowledge Graph Embeddings. (arXiv:2301.10405v5 [cs.CL] UPDATED) 

arxiv.org/abs/2301.10405

0
arXiv - CSCL

Rethinking the Role of Scale for In-Context Learning: An Interpretability-based Case Study at 66 Billion Scale. (arXiv:2212.09095v2 [cs.CL] UPDATED) 

arxiv.org/abs/2212.09095

0
arXiv - CSCL

Event and Entity Extraction from Generated Video Captions. (arXiv:2211.02982v2 [cs.CV] UPDATED) 

arxiv.org/abs/2211.02982

0
arXiv - CSCL

Analyzing the Limits of Self-Supervision in Handling Bias in Language. (arXiv:2112.08637v3 [cs.CL] UPDATED) 

arxiv.org/abs/2112.08637

0
arXiv - CSCL

Conceptualizing Machine Learning for Dynamic Information Retrieval of Electronic Health Record Notes. (arXiv:2308.08494v1 [cs.IR]) 

arxiv.org/abs/2308.08494

0
arXiv - CSCL

Time Travel in LLMs: Tracing Data Contamination in Large Language Models. (arXiv:2308.08493v1 [cs.CL]) 

arxiv.org/abs/2308.08493

0
arXiv - CSCL

Improving Audio-Visual Speech Recognition by Lip-Subword Correlation Based Visual Pre-training and Cross-Modal Fusion Encoder. (arXiv:2308.08488v1 [cs.CL]) 

arxiv.org/abs/2308.08488

0
arXiv - CSCL

TBIN: Modeling Long Textual Behavior Data for CTR Prediction. (arXiv:2308.08483v1 [cs.IR]) 

arxiv.org/abs/2308.08483

0
arXiv - CSCL

Improving CTC-AED model with integrated-CTC and auxiliary loss regularization. (arXiv:2308.08449v1 [cs.CL]) 

arxiv.org/abs/2308.08449

0
arXiv - CSCL

Mitigating the Exposure Bias in Sentence-Level Grapheme-to-Phoneme (G2P) Transduction. (arXiv:2308.08442v1 [cs.CL]) 

arxiv.org/abs/2308.08442

0
arXiv - CSCL

Knowledge-Enhanced Multi-Label Few-Shot Product Attribute-Value Extraction. (arXiv:2308.08413v1 [cs.IR]) 

arxiv.org/abs/2308.08413

0
arXiv - CSCL

Advancing continual lifelong learning in neural information retrieval: definition, dataset, framework, and empirical evaluation. (arXiv:2308.08378v1 [cs.IR]) 

arxiv.org/abs/2308.08378

0
arXiv - CSCL

SummHelper: Collaborative Human-Computer Summarization. (arXiv:2308.08363v1 [cs.CL]) 

arxiv.org/abs/2308.08363

0
arXiv - CSCL

Detoxify Language Model Step-by-Step. (arXiv:2308.08295v1 [cs.CL]) 

arxiv.org/abs/2308.08295

0
arXiv - CSCL

Pre-training with Large Language Model-based Document Expansion for Dense Passage Retrieval. (arXiv:2308.08285v1 [cs.IR]) 

arxiv.org/abs/2308.08285

0
arXiv - CSCL

Benchmarking Neural Network Generalization for Grammar Induction. (arXiv:2308.08253v1 [cs.CL]) 

arxiv.org/abs/2308.08253

0
arXiv - CSCL

TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Series. (arXiv:2308.08241v1 [cs.CL]) 

arxiv.org/abs/2308.08241

0
arXiv - CSCL

MemoChat: Tuning LLMs to Use Memos for Consistent Long-Range Open-Domain Conversation. (arXiv:2308.08239v1 [cs.CL]) 

arxiv.org/abs/2308.08239

0
Show older
Qoto Mastodon

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

Trending now

Resources

Developers

What is Mastodon?

qoto.org

More…

v3.5.19-qoto · Privacy policy