Show newer
arXiv - CSCL

Bidirectional Representations for Low Resource Spoken Language Understanding. (arXiv:2211.14320v2 [cs.CL] UPDATED) 

arxiv.org/abs/2211.14320

0
arXiv - CSCL

Knowledge Graph Embedding: A Survey from the Perspective of Representation Spaces. (arXiv:2211.03536v2 [cs.LG] UPDATED) 

arxiv.org/abs/2211.03536

0
arXiv - CSCL

Mind the Labels: Describing Relations in Knowledge Graphs With Pretrained Models. (arXiv:2210.07373v3 [cs.CL] UPDATED) 

arxiv.org/abs/2210.07373

0
arXiv - CSCL

Efficiently Enhancing Zero-Shot Performance of Instruction Following Model via Retrieval of Soft Prompt. (arXiv:2210.03029v4 [cs.CL] UPDATED) 

arxiv.org/abs/2210.03029

0
arXiv - CSCL

5q032e@SMM4H'22: Transformer-based classification of premise in tweets related to COVID-19. (arXiv:2209.03851v2 [cs.CL] UPDATED) 

arxiv.org/abs/2209.03851

0
arXiv - CSCL

Labeling Programs with Non-Programmers Indirectly via Active Examples: A Case Study with Text-to-SQL. (arXiv:2205.12422v2 [cs.CL] UPDATED) 

arxiv.org/abs/2205.12422

0
arXiv - CSCL

Speculative Decoding: Lossless Speedup of Autoregressive Translation. (arXiv:2203.16487v5 [cs.CL] UPDATED) 

arxiv.org/abs/2203.16487

0
arXiv - CSCL

Counterfactual Memorization in Neural Language Models. (arXiv:2112.12938v2 [cs.CL] UPDATED) 

arxiv.org/abs/2112.12938

0
arXiv - CSCL

Graphmax for Text Generation. (arXiv:2101.00153v2 [cs.CL] UPDATED) 

arxiv.org/abs/2101.00153

0
arXiv - CSCL

Temporal Convolutional Attention-based Network For Sequence Modeling. (arXiv:2002.12530v3 [cs.CL] UPDATED) 

arxiv.org/abs/2002.12530

0
arXiv - CSCL

Sentiment Analysis Using Averaged Weighted Word Vector Features. (arXiv:2002.05606v2 [cs.CL] UPDATED) 

arxiv.org/abs/2002.05606

0
arXiv - CSCL

Instruction Tuning with Human Curriculum. (arXiv:2310.09518v1 [cs.CL]) 

arxiv.org/abs/2310.09518

0
arXiv - CSCL

Attentive Multi-Layer Perceptron for Non-autoregressive Generation. (arXiv:2310.09512v1 [cs.CL]) 

arxiv.org/abs/2310.09512

0
arXiv - CSCL

DepNeCTI: Dependency-based Nested Compound Type Identification for Sanskrit. (arXiv:2310.09501v1 [cs.CL]) 

arxiv.org/abs/2310.09501

0
arXiv - CSCL

One-Shot Sensitivity-Aware Mixed Sparsity Pruning for Large Language Models. (arXiv:2310.09499v1 [cs.CL]) 

arxiv.org/abs/2310.09499

0
arXiv - CSCL

Computational analyses of linguistic features with schizophrenic and autistic traits along with formal thought disorders. (arXiv:2310.09494v1 [cs.CL]) 

arxiv.org/abs/2310.09494

0
arXiv - CSCL

Sub-network Discovery and Soft-masking for Continual Learning of Mixed Tasks. (arXiv:2310.09436v1 [cs.CL]) 

arxiv.org/abs/2310.09436

0
arXiv - CSCL

Enhancing BERT-Based Visual Question Answering through Keyword-Driven Sentence Selection. (arXiv:2310.09432v1 [cs.CL]) 

arxiv.org/abs/2310.09432

0
arXiv - CSCL

A Systematic Evaluation of Large Language Models on Out-of-Distribution Logical Reasoning Tasks. (arXiv:2310.09430v1 [cs.CL]) 

arxiv.org/abs/2310.09430

0
arXiv - CSCL

SALM: Speech-augmented Language Model with In-context Learning for Speech Recognition and Translation. (arXiv:2310.09424v1 [cs.CL]) 

arxiv.org/abs/2310.09424

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