SOTAVerified

Language Modeling

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 10551–10575 of 14182 papers

TitleStatusHype
Balancing Average and Worst-case Accuracy in Multitask Learning—0
Learning Compact Metrics for MTCode1
SRU++: Pioneering Fast Recurrence with Attention for Speech Recognition—0
Multi-Task Learning for Situated Multi-Domain End-to-End Dialogue Systems—0
On a Benefit of Mask Language Modeling: Robustness to Simplicity Bias—0
Unsupervised Neural Machine Translation with Generative Language Models Only—0
Evaluating User Perception of Speech Recognition System Quality with Semantic Distance Metric—0
Breaking the Softmax Bottleneck for Sequential Recommender Systems with Dropout and Decoupling—0
Frequency-aware SGD for Efficient Embedding Learning with Provable Benefits—0
Automatic Text Extractive Summarization Based on Graph and Pre-trained Language Model Attention—0
Long Expressive Memory for Sequence ModelingCode1
Yuan 1.0: Large-Scale Pre-trained Language Model in Zero-Shot and Few-Shot LearningCode1
Improving Multi-Party Dialogue Discourse Parsing via Domain IntegrationCode1
Global Explainability of BERT-Based Evaluation Metrics by Disentangling along Linguistic FactorsCode1
KaraSinger: Score-Free Singing Voice Synthesis with VQ-VAE using Mel-spectrograms—0
Layer-wise Pruning of Transformer Attention Heads for Efficient Language ModelingCode1
Improving Confidence Estimation on Out-of-Domain Data for End-to-End Speech Recognition—0
Back from the future: bidirectional CTC decoding using future information in speech recognition—0
Mixer-TTS: non-autoregressive, fast and compact text-to-speech model conditioned on language model embeddingsCode1
Beam Search with Bidirectional Strategies for Neural Response Generation—0
Internal Language Model Adaptation with Text-Only Data for End-to-End Speech Recognition—0
Cut the CARP: Fishing for zero-shot story evaluation—0
ABC: Attention with Bounded-memory Control—0
8-bit Optimizers via Block-wise QuantizationCode3
Language Modeling using LMUs: 10x Better Data Efficiency or Improved Scaling Compared to Transformers—0
Show:102550
← PrevPage 423 of 568Next →

No leaderboard results yet.