TY  - GEN
PB  - Association for Computational Linguistics
N2  - Adaptive Computation (AC) has been shown to be effective in improving the efficiency of Open-Domain Question Answering (ODQA) systems. However, the current AC approaches require tuning of all model parameters, and training state-of-the-art ODQA models requires significant computational resources that may not be available for most researchers. We propose Adaptive Passage Encoder, an AC method that can be applied to an existing ODQA model and can be trained efficiently on a single GPU. It keeps the parameters of the base ODQA model fixed, but it overrides the default layer-by-layer computation of the encoder with an AC policy that is trained to optimise the computational efficiency of the model. Our experimental results show that our method improves upon a state-of-the-art model on two datasets, and is also more accurate than previous AC methods due to the stronger base ODQA model. All source code and datasets are available at https://github.com/uclnlp/APE.
Y1  - 2021/01/01/
UR  - https://aclanthology.org/2021.acl-short.57/
N1  - ACL materials are Copyright © 1963?2021 ACL; other materials are copyrighted by their respective copyright holders. Materials prior to 2016 here are licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 3.0 International License. Permission is granted to make copies for the purposes of teaching and research. Materials published in or after 2016 are licensed on a Creative Commons Attribution 4.0 International License.
TI  - Training Adaptive Computation for Open-Domain Question Answering with Computational Constraints
AV  - public
ID  - discovery10136198
KW  - Science & Technology
KW  -  Social Sciences
KW  -  Technology
KW  -  Computer Science
KW  -  Artificial Intelligence
KW  -  Computer Science
KW  -  Interdisciplinary Applications
KW  -  Linguistics
KW  -  Computer Science
EP  - 453
SP  - 447
A1  - Wu, Y
A1  - Minervini, P
A1  - Stenetorp, P
A1  - Riedel, S
ER  -