Show newer
arXiv - CSCL

XPhoneBERT: A Pre-trained Multilingual Model for Phoneme Representations for Text-to-Speech. (arXiv:2305.19709v1 [cs.CL]) 

arxiv.org/abs/2305.19709

0
arXiv - CSCL

Building Extractive Question Answering System to Support Human-AI Health Coaching Model for Sleep Domain. (arXiv:2305.19707v1 [cs.CL]) 

arxiv.org/abs/2305.19707

0
arXiv - CSCL

Assessing Word Importance Using Models Trained for Semantic Tasks. (arXiv:2305.19689v1 [cs.CL]) 

arxiv.org/abs/2305.19689

0
arXiv - CSCL

Unveiling Cross Modality Bias in Visual Question Answering: A Causal View with Possible Worlds VQA. (arXiv:2305.19664v1 [cs.CV]) 

arxiv.org/abs/2305.19664

0
arXiv - CSCL

Adverbs, Surprisingly. (arXiv:2305.19650v1 [cs.CL]) 

arxiv.org/abs/2305.19650

0
arXiv - CSCL

Adversarial Clean Label Backdoor Attacks and Defenses on Text Classification Systems. (arXiv:2305.19607v1 [cs.CL]) 

arxiv.org/abs/2305.19607

0
arXiv - CSCL

What does the Failure to Reason with "Respectively" in Zero/Few-Shot Settings Tell Us about Language Models?. (arXiv:2305.19597v1 [cs.CL]) 

arxiv.org/abs/2305.19597

0
arXiv - CSCL

SLABERT Talk Pretty One Day: Modeling Second Language Acquisition with BERT. (arXiv:2305.19589v1 [cs.CL]) 

arxiv.org/abs/2305.19589

0
arXiv - CSCL

LAIT: Efficient Multi-Segment Encoding in Transformers with Layer-Adjustable Interaction. (arXiv:2305.19585v1 [cs.CL]) 

arxiv.org/abs/2305.19585

0
arXiv - CSCL

The Tag-Team Approach: Leveraging CLS and Language Tagging for Enhancing Multilingual ASR. (arXiv:2305.19584v1 [cs.CL]) 

arxiv.org/abs/2305.19584

0
arXiv - CSCL

DC CoMix TTS: An End-to-End Expressive TTS with Discrete Code Collaborated with Mixer. (arXiv:2305.19567v1 [cs.SD]) 

arxiv.org/abs/2305.19567

0
arXiv - CSCL

Zero-Shot Automatic Pronunciation Assessment. (arXiv:2305.19563v1 [cs.SD]) 

arxiv.org/abs/2305.19563

0
arXiv - CSCL

Large Language Models Are Not Abstract Reasoners. (arXiv:2305.19555v1 [cs.CL]) 

arxiv.org/abs/2305.19555

0
arXiv - CSCL

Accurate and Structured Pruning for Efficient Automatic Speech Recognition. (arXiv:2305.19549v1 [cs.CL]) 

arxiv.org/abs/2305.19549

0
arXiv - CSCL

Fine-grained Text Style Transfer with Diffusion-Based Language Models. (arXiv:2305.19512v1 [cs.CL]) 

arxiv.org/abs/2305.19512

0
arXiv - CSCL

Exploring Lottery Prompts for Pre-trained Language Models. (arXiv:2305.19500v1 [cs.CL]) 

arxiv.org/abs/2305.19500

0
arXiv - CSCL

Towards Flow Graph Prediction of Open-Domain Procedural Texts. (arXiv:2305.19497v1 [cs.CL]) 

arxiv.org/abs/2305.19497

0
arXiv - CSCL

Ethical Considerations for Machine Translation of Indigenous Languages: Giving a Voice to the Speakers. (arXiv:2305.19474v1 [cs.CL]) 

arxiv.org/abs/2305.19474

0
arXiv - CSCL

PlaSma: Making Small Language Models Better Procedural Knowledge Models for (Counterfactual) Planning. (arXiv:2305.19472v1 [cs.CL]) 

arxiv.org/abs/2305.19472

0
arXiv - CSCL

The Impact of Positional Encoding on Length Generalization in Transformers. (arXiv:2305.19466v1 [cs.CL]) 

arxiv.org/abs/2305.19466

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