Abstract is missing.
- KwikBucks: Correlation Clustering with Cheap-Weak and Expensive-Strong SignalsSandeep Silwal, Sara Ahmadian, Andrew Nystrom, Andrew McCallum, Deepak Ramachandran, Seyed Mehran Kazemi. 1-31 [doi]
- Semantic-Oriented Unlabeled Priming for Large-Scale Language ModelsYanchen Liu, Timo Schick, Hinrich Schtze. 32-38 [doi]
- oBERTa: Improving Sparse Transfer Learning via improved initialization, distillation, and pruning regimesDaniel Campos, Alexandre Marques, Mark Kurtz, ChengXiang Zhai. 39-58 [doi]
- Quick Dense Retrievers Consume KALE: Post Training KullbackLeibler Alignment of Embeddings for Asymmetrical dual encodersDaniel Campos, Alessandro Magnani, ChengXiang Zhai. 59-77 [doi]
- Lessons on Parameter Sharing across Layers in TransformersSho Takase, Shun Kiyono. 78-90 [doi]
- To Asymmetry and Beyond: Structured Pruning of Sequence to Sequence Models for Improved Inference EfficiencyDaniel Campos, ChengXiang Zhai. 91-109 [doi]
- Small is the New Big: Pre-finetuned compact models are better for Asynchronous Active LearningDantong Liu, Kaushik Pavani, Sunny Dasgupta. 110-120 [doi]
- ADEPT: Adapter-based Efficient Prompt Tuning Approach for Language ModelsAditya Shah, Surendrabikram Thapa, Aneesh Jain, Lifu Huang. 121-128 [doi]
- NLU on Data Diets: Dynamic Data Subset Selection for NLP Classification TasksJean-Michel Attendu, Jean-Philippe Corbeil. 129-146 [doi]
- On the Interactions of Structural Constraints and Data Resources for Structured PredictionZhisong Zhang, Emma Strubell, Eduard H. Hovy. 147-157 [doi]
- Can we Pretrain a SotA Legal Language Model on a Budget From Scratch?Joel Niklaus, Daniele Giofré. 158-182 [doi]
- Is a Video worth n n Images? A Highly Efficient Approach to Transformer-based Video Question AnsweringChenyang Lyu, Tianbo Ji, Yvette Graham, Jennifer Foster. 183-189 [doi]
- How to Unleash the Power of Large Language Models for Few-shot Relation Extraction?Xin Xu, Yuqi Zhu, Xiaohan Wang, Ningyu Zhang 0001. 190-200 [doi]
- Prompting language models improves performance in imbalanced settingJay Mohta. 201-211 [doi]
- KGQA Without RetrainingNick McKenna, Priyanka Sen. 212-218 [doi]
- MANER: Mask Augmented Named Entity Recognition for Extreme Low-Resource LanguagesShashank Sonkar, Zichao Wang 0001, Richard G. Baraniuk. 219-226 [doi]
- Efficient and Interpretable Compressive Text Summarisation with Unsupervised Dual-Agent Reinforcement LearningPeggy Tang, Junbin Gao, Lei Zhang, Zhiyong Wang 0001. 227-238 [doi]
- Exploring the Effect of Frequency Resolution in FNetGregory Szumel, Ghazal Khalighinejad, Rickard Stureborg, Sam Wiseman. 239-244 [doi]
- Towards Adaptable and Interactive Image Captioning with Data Augmentation and Episodic MemoryAliki Anagnostopoulou, Mareike Hartmann, Daniel Sonntag. 245-256 [doi]
- Corpus Complexity Matters in Pretraining Language ModelsAmeeta Agrawal, Suresh Singh. 257-263 [doi]
- PersonaPKT: Building Personalized Dialogue Agents via Parameter-efficient Knowledge TransferXu Han, Bin Guo, Yoon Jung, Benjamin Yao, Yu Zhang, Xiaohu Liu, Chenlei Guo. 264-273 [doi]
- Small Character Models Match Large Word Models for Autocomplete Under Memory ConstraintsGanesh Jawahar, Subhabrata Mukherjee, Debadeepta Dey, Muhammad Abdul-Mageed, Laks V. S. Lakshmanan, Caio Mendes, Gustavo de Rosa, Shital Shah. 274-289 [doi]
- Query Encoder Distillation via Embedding Alignment is a Strong Baseline Method to Boost Dense Retriever Online EfficiencyYuxuan Wang, Hong Lyu. 290-298 [doi]
- Minimalist Entity Disambiguation for Mid-Resource LanguagesBenno Kruit. 299-306 [doi]