Ensemble Transformer for Efficient and Accurate Ranking Tasks: an Application to Question Answering Systems
| Autor: | Matsubara, Yoshitomo, Soldaini, Luca, Lind, Eric, Moschitti, Alessandro |
|---|---|
| Rok vydání: | 2022 |
| Předmět: | |
| Zdroj: | Findings of the Association for Computational Linguistics: EMNLP 2022 |
| Druh dokumentu: | Working Paper |
| Popis: | Large transformer models can highly improve Answer Sentence Selection (AS2) tasks, but their high computational costs prevent their use in many real-world applications. In this paper, we explore the following research question: How can we make the AS2 models more accurate without significantly increasing their model complexity? To address the question, we propose a Multiple Heads Student architecture (named CERBERUS), an efficient neural network designed to distill an ensemble of large transformers into a single smaller model. CERBERUS consists of two components: a stack of transformer layers that is used to encode inputs, and a set of ranking heads; unlike traditional distillation technique, each of them is trained by distilling a different large transformer architecture in a way that preserves the diversity of the ensemble members. The resulting model captures the knowledge of heterogeneous transformer models by using just a few extra parameters. We show the effectiveness of CERBERUS on three English datasets for AS2; our proposed approach outperforms all single-model distillations we consider, rivaling the state-of-the-art large AS2 models that have 2.7x more parameters and run 2.5x slower. Code for our model is available at https://github.com/amazon-research/wqa-cerberus Comment: Accepted to EMNLP 2022 as a long paper (Findings). Model code is available at https://github.com/amazon-research/wqa-cerberus |
| Databáze: | arXiv |
| Externí odkaz: |
|