Pretraining

TaiSu: A 166M Large-scale High-Quality Dataset for Chinese Vision-Language Pre-training NeurIPS 2022 TAPEX: Table Pre-training via Learning a Neural SQL Executor ICLR 2022 Task Compass: Scaling Multi-task Pre-training with Task Prefix EMNLP 2022 Task-Customized Self-Supervised Pre-training with Scalable Dynamic Routing AAAI 2022 TeamOtter at SemEval-2022 Task 5: Detecting Misogynistic Content in Multimodal Memes SemEval 2022 The Inductive Bias of In-Context Learning: Rethinking Pretraining Example Design ICLR 2022 The SIGTYP 2022 Shared Task on the Prediction of Cognate Reflexes NAACL 2022 The THUEE System Description for the IARPA OpenASR21 Challenge Interspeech 2022 The ZevoMOS entry to VoiceMOS Challenge 2022 Interspeech 2022 Tokenwise Contrastive Pretraining for Finer Speech-to-BERT Alignment in End-to-End Speech-to-Intent Systems Interspeech 2022 Towards high-fidelity singing voice conversion with acoustic reference and contrastive predictive coding Interspeech 2022 Towards Improving the Expressiveness of Singing Voice Synthesis with BERT Derived Semantic Information Interspeech 2022 Towards Understanding Large-Scale Discourse Structures in Pre-Trained and Fine-Tuned Language Models NAACL 2022 Towards Weakly-Supervised Text Spotting Using a Multi-Task Transformer CVPR 2022 TransBoost: Improving the Best ImageNet Performance using Deep Transduction NeurIPS 2022 Transformers on Multilingual Clause-Level Morphology EMNLP 2022 Translating Spanish into Spanish Sign Language: Combining Rules and Data-driven Approaches COLING 2022 Translation between Molecules and Natural Language EMNLP 2022 TRIPS: Efficient Vision-and-Language Pre-training with Text-Relevant Image Patch Selection EMNLP 2022 TSTR: Too Short to Represent, Summarize with Details! Intro-Guided Extended Summary Generation NAACL 2022 TVLT: Textless Vision-Language Transformer NeurIPS 2022 UMUTeam at SemEval-2022 Task 6: Evaluating Transformers for detecting Sarcasm in English and Arabic SemEval 2022 Understanding Multimodal Procedural Knowledge by Sequencing Multimodal Instructional Manuals ACL 2022 UniFormer: Unified Transformer for Efficient Spatial-Temporal Representation Learning ICLR 2022 UNIMO-2: End-to-End Unified Vision-Language Grounded Learning ACL 2022