Nothing Special   »   [go: up one dir, main page]

Optimizing Retrieval-augmented Reader Models via Token Elimination

Moshe Berchansky, Peter Izsak, Avi Caciularu, Ido Dagan, Moshe Wasserblat


Abstract
Fusion-in-Decoder (FiD) is an effective retrieval-augmented language model applied across a variety of open-domain tasks, such as question answering, fact checking, etc. In FiD, supporting passages are first retrieved and then processed using a generative model (Reader), which can cause a significant bottleneck in decoding time, particularly with long outputs. In this work, we analyze the contribution and necessity of all the retrieved passages to the performance of reader models, and propose eliminating some of the retrieved information, at the token level, that might not contribute essential information to the answer generation process. We demonstrate that our method can reduce run-time by up to 62.2%, with only a 2% reduction in performance, and in some cases, even improve the performance results.
Anthology ID:
2023.emnlp-main.93
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1506–1524
Language:
URL:
https://aclanthology.org/2023.emnlp-main.93
DOI:
10.18653/v1/2023.emnlp-main.93
Bibkey:
Cite (ACL):
Moshe Berchansky, Peter Izsak, Avi Caciularu, Ido Dagan, and Moshe Wasserblat. 2023. Optimizing Retrieval-augmented Reader Models via Token Elimination. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 1506–1524, Singapore. Association for Computational Linguistics.
Cite (Informal):
Optimizing Retrieval-augmented Reader Models via Token Elimination (Berchansky et al., EMNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.emnlp-main.93.pdf
Video:
 https://aclanthology.org/2023.emnlp-main.93.mp4