Search Results for author:
Found 4 papers, 1 papers with code
Combining Compressions for Multiplicative Size Scaling on Natural Language Tasks
Our work quantitatively demonstrates that combining compression methods can synergistically reduce model size, and that practitioners should prioritize (1) quantization, (2) knowledge distillation, and (3) pruning to maximize accuracy vs. model size tradeoffs.
Active Learning Over Multiple Domains in Natural Language Tasks
Studies of active learning traditionally assume the target and source data stem from a single domain.
Entity-Based Knowledge Conflicts in Question Answering
To understand how models use these sources together, we formalize the problem of knowledge conflicts, where the contextual information contradicts the learned information.
An Exploration of Data Augmentation and Sampling Techniques for Domain-Agnostic Question Answering
To produce a domain-agnostic question answering model for the Machine Reading Question Answering (MRQA) 2019 Shared Task, we investigate the relative benefits of large pre-trained language models, various data sampling strategies, as well as query and context paraphrases generated by back-translation.
