Show newer
arXiv - CSCL

Arabic Dysarthric Speech Recognition Using Adversarial and Signal-Based Augmentation. (arXiv:2306.04368v1 [cs.SD]) 

arxiv.org/abs/2306.04368

0
arXiv - CSCL

Youku-mPLUG: A 10 Million Large-scale Chinese Video-Language Dataset for Pre-training and Benchmarks. (arXiv:2306.04362v1 [cs.CV]) 

arxiv.org/abs/2306.04362

0
arXiv - CSCL

ConTextual Masked Auto-Encoder for Retrieval-based Dialogue Systems. (arXiv:2306.04357v1 [cs.CL]) 

arxiv.org/abs/2306.04357

0
arXiv - CSCL

GPT Self-Supervision for a Better Data Annotator. (arXiv:2306.04349v1 [cs.CL]) 

arxiv.org/abs/2306.04349

0
arXiv - CSCL

World Models for Math Story Problems. (arXiv:2306.04347v1 [cs.CL]) 

arxiv.org/abs/2306.04347

0
arXiv - CSCL

Co-evolving Graph Reasoning Network for Emotion-Cause Pair Extraction. (arXiv:2306.04340v1 [cs.CL]) 

arxiv.org/abs/2306.04340

0
arXiv - CSCL

A Study on the Reliability of Automatic Dysarthric Speech Assessments. (arXiv:2306.04337v1 [cs.CL]) 

arxiv.org/abs/2306.04337

0
arXiv - CSCL

Echoes from Alexandria: A Large Resource for Multilingual Book Summarization. (arXiv:2306.04334v1 [cs.CL]) 

arxiv.org/abs/2306.04334

0
arXiv - CSCL

IUTEAM1 at MEDIQA-Chat 2023: Is simple fine tuning effective for multilayer summarization of clinical conversations?. (arXiv:2306.04328v1 [cs.CL]) 

arxiv.org/abs/2306.04328

0
arXiv - CSCL

Cross-Genre Argument Mining: Can Language Models Automatically Fill in Missing Discourse Markers?. (arXiv:2306.04314v1 [cs.CL]) 

arxiv.org/abs/2306.04314

0
arXiv - CSCL

Personality testing of GPT-3: Limited temporal reliability, but highlighted social desirability of GPT-3's personality instruments results. (arXiv:2306.04308v1 [cs.AI]) 

arxiv.org/abs/2306.04308

0
arXiv - CSCL

Allophant: Cross-lingual Phoneme Recognition with Articulatory Attributes. (arXiv:2306.04306v1 [cs.CL]) 

arxiv.org/abs/2306.04306

0
arXiv - CSCL

Phrase Retrieval for Open-Domain Conversational Question Answering with Conversational Dependency Modeling via Contrastive Learning. (arXiv:2306.04293v1 [cs.CL]) 

arxiv.org/abs/2306.04293

0
arXiv - CSCL

Analysis of the Fed's communication by using textual entailment model of Zero-Shot classification. (arXiv:2306.04277v1 [cs.CL]) 

arxiv.org/abs/2306.04277

0
arXiv - CSCL

Multi-microphone Automatic Speech Segmentation in Meetings Based on Circular Harmonics Features. (arXiv:2306.04268v1 [cs.SD]) 

arxiv.org/abs/2306.04268

0
arXiv - CSCL

Transfer Learning from Pre-trained Language Models Improves End-to-End Speech Summarization. (arXiv:2306.04233v1 [cs.CL]) 

arxiv.org/abs/2306.04233

0
arXiv - CSCL

Effective Neural Topic Modeling with Embedding Clustering Regularization. (arXiv:2306.04217v1 [cs.CL]) 

arxiv.org/abs/2306.04217

0
arXiv - CSCL

Leveraging Knowledge Graph Embeddings to Enhance Contextual Representations for Relation Extraction. (arXiv:2306.04203v1 [cs.CL]) 

arxiv.org/abs/2306.04203

0
arXiv - CSCL

An ASR-Based Tutor for Learning to Read: How to Optimize Feedback to First Graders. (arXiv:2306.04190v1 [cs.CL]) 

arxiv.org/abs/2306.04190

0
arXiv - CSCL

A New Dataset and Empirical Study for Sentence Simplification in Chinese. (arXiv:2306.04188v1 [cs.CL]) 

arxiv.org/abs/2306.04188

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