Show newer
arXiv - CSCL

High-Quality Automatic Voice Over with Accurate Alignment: Supervision through Self-Supervised Discrete Speech Units. (arXiv:2306.17005v1 [eess.AS]) 

arxiv.org/abs/2306.17005

0
arXiv - CSCL

MEMD-ABSA: A Multi-Element Multi-Domain Dataset for Aspect-Based Sentiment Analysis. (arXiv:2306.16956v1 [cs.CL]) 

arxiv.org/abs/2306.16956

0
arXiv - CSCL

Predicting Music Hierarchies with a Graph-Based Neural Decoder. (arXiv:2306.16955v1 [cs.SD]) 

arxiv.org/abs/2306.16955

0
arXiv - CSCL

UMASS_BioNLP at MEDIQA-Chat 2023: Can LLMs generate high-quality synthetic note-oriented doctor-patient conversations?. (arXiv:2306.16931v1 [cs.CL]) 

arxiv.org/abs/2306.16931

0
arXiv - CSCL

Leveraging Cross-Utterance Context For ASR Decoding. (arXiv:2306.16903v1 [cs.CL]) 

arxiv.org/abs/2306.16903

0
arXiv - CSCL

Surveying (Dis)Parities and Concerns of Compute Hungry NLP Research. (arXiv:2306.16900v1 [cs.CL]) 

arxiv.org/abs/2306.16900

0
arXiv - CSCL

Tokenization and the Noiseless Channel. (arXiv:2306.16842v1 [cs.CL]) 

arxiv.org/abs/2306.16842

0
arXiv - CSCL

A Formal Perspective on Byte-Pair Encoding. (arXiv:2306.16837v1 [cs.CL]) 

arxiv.org/abs/2306.16837

0
arXiv - CSCL

CLIPAG: Towards Generator-Free Text-to-Image Generation. (arXiv:2306.16805v1 [cs.CV]) 

arxiv.org/abs/2306.16805

0
arXiv - CSCL

Benchmarking Large Language Model Capabilities for Conditional Generation. (arXiv:2306.16793v1 [cs.CL]) 

arxiv.org/abs/2306.16793

0
arXiv - CSCL

Stop Pre-Training: Adapt Visual-Language Models to Unseen Languages. (arXiv:2306.16774v1 [cs.CL]) 

arxiv.org/abs/2306.16774

0
arXiv - CSCL

DialoGPS: Dialogue Path Sampling in Continuous Semantic Space for Data Augmentation in Multi-Turn Conversations. (arXiv:2306.16770v1 [cs.CL]) 

arxiv.org/abs/2306.16770

0
arXiv - CSCL

Unified Language Representation for Question Answering over Text, Tables, and Images. (arXiv:2306.16762v1 [cs.CL]) 

arxiv.org/abs/2306.16762

0
arXiv - CSCL

Evaluating Paraphrastic Robustness in Textual Entailment Models. (arXiv:2306.16722v1 [cs.CL]) 

arxiv.org/abs/2306.16722

0
arXiv - CSCL

Automatic Speech Recognition of Non-Native Child Speech for Language Learning Applications. (arXiv:2306.16710v1 [cs.CL]) 

arxiv.org/abs/2306.16710

0
arXiv - CSCL

Multi-source Semantic Graph-based Multimodal Sarcasm Explanation Generation. (arXiv:2306.16650v1 [cs.CL]) 

arxiv.org/abs/2306.16650

0
arXiv - CSCL

ZeroGen: Zero-shot Multimodal Controllable Text Generation with Multiple Oracles. (arXiv:2306.16649v1 [cs.CL]) 

arxiv.org/abs/2306.16649

0
arXiv - CSCL

Probabilistic Linguistic Knowledge and Token-level Text Augmentation. (arXiv:2306.16644v1 [cs.CL]) 

arxiv.org/abs/2306.16644

0
arXiv - CSCL

A negation detection assessment of GPTs: analysis with the xNot360 dataset. (arXiv:2306.16638v1 [cs.CL]) 

arxiv.org/abs/2306.16638

0
arXiv - CSCL

CMATH: Can Your Language Model Pass Chinese Elementary School Math Test?. (arXiv:2306.16636v1 [cs.CL]) 

arxiv.org/abs/2306.16636

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.

Resources

Developers

What is Mastodon?

qoto.org

More…

v3.5.19-qoto · Privacy policy