Benchmarking a transformer-FREE model for ad-hoc retrieval

Tiago Almeida, Sérgio Matos


Abstract
Transformer-based “behemoths” have grown in popularity, as well as structurally, shattering multiple NLP benchmarks along the way. However, their real-world usability remains a question. In this work, we empirically assess the feasibility of applying transformer-based models in real-world ad-hoc retrieval applications by comparison to a “greener and more sustainable” alternative, comprising only 620 trainable parameters. We present an analysis of their efficacy and efficiency and show that considering limited computational resources, the lighter model running on the CPU achieves a 3 to 20 times speedup in training and 7 to 47 times in inference while maintaining a comparable retrieval performance. Code to reproduce the efficiency experiments is available on “https://github.com/bioinformatics-ua/EACL2021-reproducibility/“.
Anthology ID:
2021.eacl-main.293
Volume:
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
Month:
April
Year:
2021
Address:
Online
Editors:
Paola Merlo, Jorg Tiedemann, Reut Tsarfaty
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3343–3353
Language:
URL:
https://aclanthology.org/2021.eacl-main.293
DOI:
10.18653/v1/2021.eacl-main.293
Bibkey:
Cite (ACL):
Tiago Almeida and Sérgio Matos. 2021. Benchmarking a transformer-FREE model for ad-hoc retrieval. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 3343–3353, Online. Association for Computational Linguistics.
Cite (Informal):
Benchmarking a transformer-FREE model for ad-hoc retrieval (Almeida & Matos, EACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.eacl-main.293.pdf
Code
 bioinformatics-ua/EACL2021-reproducibility
Data
CORD-19