Show newer
arXiv - CSCL

Disentangling Prosody Representations with Unsupervised Speech Reconstruction. (arXiv:2212.06972v1 [cs.SD]) 

arxiv.org/abs/2212.06972

0
arXiv - CSCL

Find Someone Who: Visual Commonsense Understanding in Human-Centric Grounding. (arXiv:2212.06971v1 [cs.CV]) 

arxiv.org/abs/2212.06971

0
arXiv - CSCL

Pre-trained Language Models can be Fully Zero-Shot Learners. (arXiv:2212.06950v1 [cs.CL]) 

arxiv.org/abs/2212.06950

0
arXiv - CSCL

Paraphrase Identification with Deep Learning: A Review of Datasets and Methods. (arXiv:2212.06933v1 [cs.CL]) 

arxiv.org/abs/2212.06933

0
arXiv - CSCL

Envisioning a Human-AI collaborative system to transform policies into decision models. (arXiv:2212.06882v1 [cs.AI]) 

arxiv.org/abs/2212.06882

0
arXiv - CSCL

Deep Image Style Transfer from Freeform Text. (arXiv:2212.06868v1 [cs.CV]) 

arxiv.org/abs/2212.06868

0
arXiv - CSCL

Technological taxonomies for hypernym and hyponym retrieval in patent texts. (arXiv:2212.06039v2 [cs.CL] CROSS LISTED) 

arxiv.org/abs/2212.06039

0
arXiv - CSCL

Automated ICD Coding using Extreme Multi-label Long Text Transformer-based Models. (arXiv:2212.05857v2 [cs.CL] UPDATED) 

arxiv.org/abs/2212.05857

0
arXiv - CSCL

Reasoning over Different Types of Knowledge Graphs: Static, Temporal and Multi-Modal. (arXiv:2212.05767v2 [cs.AI] UPDATED) 

arxiv.org/abs/2212.05767

0
arXiv - CSCL

Extending TrOCR for Text Localization-Free OCR of Full-Page Scanned Receipt Images. (arXiv:2212.05525v2 [cs.CL] UPDATED) 

arxiv.org/abs/2212.05525

0
arXiv - CSCL

IndicXTREME: A Multi-Task Benchmark For Evaluating Indic Languages. (arXiv:2212.05409v2 [cs.CL] UPDATED) 

arxiv.org/abs/2212.05409

0
arXiv - CSCL

Pivotal Role of Language Modeling in Recommender Systems: Enriching Task-specific and Task-agnostic Representation Learning. (arXiv:2212.03760v2 [cs.IR] UPDATED) 

arxiv.org/abs/2212.03760

0
arXiv - CSCL

Continual Learning for On-Device Speech Recognition using Disentangled Conformers. (arXiv:2212.01393v2 [eess.AS] UPDATED) 

arxiv.org/abs/2212.01393

0
arXiv - CSCL

Keywords Reinforcement LM: Improving End-to-End Response Generation in Task Oriented Dialog. (arXiv:2211.16773v2 [cs.CL] UPDATED) 

arxiv.org/abs/2211.16773

0
arXiv - CSCL

PCRED: Zero-shot Relation Triplet Extraction with Potential Candidate Relation Selection and Entity Boundary Detection. (arXiv:2211.14477v2 [cs.CL] UPDATED) 

arxiv.org/abs/2211.14477

0
arXiv - CSCL

UniSumm: Unified Few-shot Summarization with Multi-Task Pre-Training and Prefix-Tuning. (arXiv:2211.09783v4 [cs.CL] UPDATED) 

arxiv.org/abs/2211.09783

0
arXiv - CSCL

Towards Building Text-To-Speech Systems for the Next Billion Users. (arXiv:2211.09536v2 [cs.CL] UPDATED) 

arxiv.org/abs/2211.09536

0
arXiv - CSCL

The Effect of Multiple Replies for Natural Language Generation Chatbots. (arXiv:2210.17209v2 [cs.HC] UPDATED) 

arxiv.org/abs/2210.17209

0
arXiv - CSCL

Solving Math Word Problem via Cooperative Reasoning induced Language Models. (arXiv:2210.16257v2 [cs.CL] UPDATED) 

arxiv.org/abs/2210.16257

0
arXiv - CSCL

Learning to Reuse Distractors to support Multiple Choice Question Generation in Education. (arXiv:2210.13964v2 [cs.CL] UPDATED) 

arxiv.org/abs/2210.13964

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