Show newer
arXiv - CSCL

SIFTER: A Task-specific Alignment Strategy for Enhancing Sentence Embeddings. (arXiv:2306.12280v1 [cs.CL]) 

arxiv.org/abs/2306.12280

0
arXiv - CSCL

Solving and Generating NPR Sunday Puzzles with Large Language Models. (arXiv:2306.12255v1 [cs.CL]) 

arxiv.org/abs/2306.12255

0
arXiv - CSCL

Bidirectional End-to-End Learning of Retriever-Reader Paradigm for Entity Linking. (arXiv:2306.12245v1 [cs.CL]) 

arxiv.org/abs/2306.12245

0
arXiv - CSCL

Limits for Learning with Language Models. (arXiv:2306.12213v1 [cs.CL]) 

arxiv.org/abs/2306.12213

0
arXiv - CSCL

Investigating Pre-trained Language Models on Cross-Domain Datasets, a Step Closer to General AI. (arXiv:2306.12205v1 [cs.CL]) 

arxiv.org/abs/2306.12205

0
arXiv - CSCL

Opening the Black Box: Analyzing Attention Weights and Hidden States in Pre-trained Language Models for Non-language Tasks. (arXiv:2306.12198v1 [cs.CL]) 

arxiv.org/abs/2306.12198

0
arXiv - CSCL

Feature Interactions Reveal Linguistic Structure in Language Models. (arXiv:2306.12181v1 [cs.CL]) 

arxiv.org/abs/2306.12181

0
arXiv - CSCL

Mixture Encoder for Joint Speech Separation and Recognition. (arXiv:2306.12173v1 [cs.CL]) 

arxiv.org/abs/2306.12173

0
arXiv - CSCL

Which Spurious Correlations Impact Reasoning in NLI Models? A Visual Interactive Diagnosis through Data-Constrained Counterfactuals. (arXiv:2306.12146v1 [cs.CL]) 

arxiv.org/abs/2306.12146

0
arXiv - CSCL

Mass-Producing Failures of Multimodal Systems with Language Models. (arXiv:2306.12105v1 [cs.LG]) 

arxiv.org/abs/2306.12105

0
arXiv - CSCL

Towards Accurate Translation via Semantically Appropriate Application of Lexical Constraints. (arXiv:2306.12089v1 [cs.CL]) 

arxiv.org/abs/2306.12089

0
arXiv - CSCL

Modeling Hierarchical Reasoning Chains by Linking Discourse Units and Key Phrases for Reading Comprehension. (arXiv:2306.12069v1 [cs.CL]) 

arxiv.org/abs/2306.12069

0
arXiv - CSCL

Sample Attackability in Natural Language Adversarial Attacks. (arXiv:2306.12043v1 [cs.CL]) 

arxiv.org/abs/2306.12043

0
arXiv - CSCL

Strategies in Transfer Learning for Low-Resource Speech Synthesis: Phone Mapping, Features Input, and Source Language Selection. (arXiv:2306.12040v1 [cs.CL]) 

arxiv.org/abs/2306.12040

0
arXiv - CSCL

Visual-Aware Text-to-Speech. (arXiv:2306.12020v1 [eess.AS]) 

arxiv.org/abs/2306.12020

0
arXiv - CSCL

A Semi-Autoregressive Graph Generative Model for Dependency Graph Parsing. (arXiv:2306.12018v1 [cs.CL]) 

arxiv.org/abs/2306.12018

0
arXiv - CSCL

3HAN: A Deep Neural Network for Fake News Detection. (arXiv:2306.12014v1 [cs.LG]) 

arxiv.org/abs/2306.12014

0
arXiv - CSCL

Interactive Molecular Discovery with Natural Language. (arXiv:2306.11976v1 [cs.CL]) 

arxiv.org/abs/2306.11976

0
arXiv - CSCL

Towards Understanding What Code Language Models Learned. (arXiv:2306.11943v1 [cs.SE]) 

arxiv.org/abs/2306.11943

0
arXiv - CSCL

Opportunities and Risks of LLMs for Scalable Deliberation with Polis. (arXiv:2306.11932v1 [cs.SI]) 

arxiv.org/abs/2306.11932

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