@inproceedings{Yang2022ECIR,
author = {Yang, Eugene and MacAvaney, Sean and Lewis, David D. and Frieder, Ophir},
title = {Goldilocks: Just-Right Tuning of BERT for Technology-Assisted Review},
year = {2022},
isbn = {978-3-030-99735-9},
publisher = {Springer-Verlag},
address = {Berlin, Heidelberg},
url = {https://doi.org/10.1007/978-3-030-99736-6_34},
doi = {10.1007/978-3-030-99736-6_34},
abstract = {Technology-assisted review (TAR) refers to iterative active learning workflows for document review in high recall retrieval (HRR) tasks. TAR research and most commercial TAR software have applied linear models such as logistic regression to lexical features. Transformer-based models with supervised tuning are known to improve effectiveness on many text classification tasks, suggesting their use in TAR. We indeed find that the pre-trained BERT model reduces review cost by 10\% to 15\% in TAR workflows simulated on the RCV1-v2 newswire collection. In contrast, we likewise determined that linear models outperform BERT for simulated legal discovery topics on the Jeb Bush e-mail collection. This suggests the match between transformer pre-training corpora and the task domain is of greater significance than generally appreciated. Additionally, we show that just-right language model fine-tuning on the task collection before starting active learning is critical. Too little or too much fine-tuning hinders performance, worse than that of linear models, even for a favorable corpus such as RCV1-v2.},
booktitle = {Advances in Information Retrieval: 44th European Conference on IR Research, ECIR 2022, Stavanger, Norway, April 10–14, 2022, Proceedings, Part I},
pages = {502–517},
numpages = {16},
location = {Stavanger, Norway}
}