Efficiency

Bridging the Training-Inference Gap for Dense Phrase Retrieval

Improving dense phrase retrieval with unfied loss and hard negatives based on efficient validation using subcorpus - ___[Findings of EMNLP 2022](https://2022.emnlp.org)___

Dynamic-TinyBERT: Boost TinyBERT's Inference Efficiency by Dynamic Sequence Length

Dynamic sequence length reduction for a TinyBERT model - ___[ENLSP NeurIPS Workshop 2021](https://neurips2021-nlp.github.io)___

Length-Adaptive Transformer: Train Once with Length Drop, Use Anytime with Search

Framework of training any transformer with length drop and using it for anytime prediction with a multi-objective evolutionary search - ___[ACL 2021](https://2021.aclweb.org)___