Show newer

Task-Specific Embeddings for Ante-Hoc Explainable Text Classification. (arXiv:2212.00086v1 [cs.CL]) 

Operationalizing Specifications, In Addition to Test Sets for Evaluating Constrained Generative Models. (arXiv:2212.00006v1 [cs.HC]) 

Enhancing and Adversarial: Improve ASR with Speaker Labels. (arXiv:2211.06369v1 [eess.AS] CROSS LISTED) 

Multimodal Analogical Reasoning over Knowledge Graphs. (arXiv:2210.00312v2 [cs.CL] CROSS LISTED) 

Relphormer: Relational Graph Transformer for Knowledge Graph Representations. (arXiv:2205.10852v4 [cs.CL] CROSS LISTED) 

Good Visual Guidance Makes A Better Extractor: Hierarchical Visual Prefix for Multimodal Entity and Relation Extraction. (arXiv:2205.03521v1 [cs.CL] CROSS LISTED) 

Hybrid Transformer with Multi-level Fusion for Multimodal Knowledge Graph Completion. (arXiv:2205.02357v4 [cs.CL] CROSS LISTED) 

From Discrimination to Generation: Knowledge Graph Completion with Generative Transformer. (arXiv:2202.02113v6 [cs.CL] CROSS LISTED) 

BotSIM: An End-to-End Bot Simulation Toolkit for Commercial Task-Oriented Dialog Systems. (arXiv:2211.15916v2 [cs.CL] UPDATED) 

DiffusionBERT: Improving Generative Masked Language Models with Diffusion Models. (arXiv:2211.15029v2 [cs.CL] UPDATED) 

BotSIM: An End-to-End Bot Simulation Framework for Commercial Task-Oriented Dialog Systems. (arXiv:2211.11982v3 [cs.CL] UPDATED) 

SMAUG: Sparse Masked Autoencoder for Efficient Video-Language Pre-training. (arXiv:2211.11446v3 [cs.CV] UPDATED) 

Cracking Double-Blind Review: Authorship Attribution with Deep Learning. (arXiv:2211.07467v2 [cs.CL] UPDATED) 

Calibrated Interpretation: Confidence Estimation in Semantic Parsing. (arXiv:2211.07443v3 [cs.CL] UPDATED) 

Efficient Adversarial Training with Robust Early-Bird Tickets. (arXiv:2211.07263v3 [cs.CL] UPDATED) 

GreenPLM: Cross-lingual pre-trained language models conversion with (almost) no cost. (arXiv:2211.06993v2 [cs.CL] UPDATED) 

Efficiently Trained Mongolian Text-to-Speech System Based On FullConv. (arXiv:2211.01948v2 [cs.CL] UPDATED) 

Joint Chinese Word Segmentation and Span-based Constituency Parsing. (arXiv:2211.01638v2 [cs.CL] UPDATED) 

Stop Measuring Calibration When Humans Disagree. (arXiv:2210.16133v2 [cs.CL] UPDATED) 

Efficient Use of Large Pre-Trained Models for Low Resource ASR. (arXiv:2210.15445v2 [eess.AS] UPDATED) 

Show older
Qoto Mastodon

QOTO: Question Others to Teach Ourselves
An inclusive, Academic Freedom, instance
All cultures welcome.
Hate speech and harassment strictly forbidden.