Combining Lexical and Dense Retrieval for Computationally Efficient Multi-hop Question Answering

Georgios Sidiropoulos, Nikos Voskarides, Svitlana Vakulenko, Evangelos Kanoulas


Abstract
In simple open-domain question answering (QA), dense retrieval has become one of the standard approaches for retrieving the relevant passages to infer an answer. Recently, dense retrieval also achieved state-of-the-art results in multi-hop QA, where aggregating information from multiple pieces of information and reasoning over them is required. Despite their success, dense retrieval methods are computationally intensive, requiring multiple GPUs to train. In this work, we introduce a hybrid (lexical and dense) retrieval approach that is highly competitive with the state-of-the-art dense retrieval models, while requiring substantially less computational resources. Additionally, we provide an in-depth evaluation of dense retrieval methods on limited computational resource settings, something that is missing from the current literature.
Anthology ID:
2021.sustainlp-1.7
Volume:
Proceedings of the Second Workshop on Simple and Efficient Natural Language Processing
Month:
November
Year:
2021
Address:
Virtual
Editors:
Nafise Sadat Moosavi, Iryna Gurevych, Angela Fan, Thomas Wolf, Yufang Hou, Ana Marasović, Sujith Ravi
Venue:
sustainlp
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
58–63
Language:
URL:
https://aclanthology.org/2021.sustainlp-1.7
DOI:
10.18653/v1/2021.sustainlp-1.7
Bibkey:
Cite (ACL):
Georgios Sidiropoulos, Nikos Voskarides, Svitlana Vakulenko, and Evangelos Kanoulas. 2021. Combining Lexical and Dense Retrieval for Computationally Efficient Multi-hop Question Answering. In Proceedings of the Second Workshop on Simple and Efficient Natural Language Processing, pages 58–63, Virtual. Association for Computational Linguistics.
Cite (Informal):
Combining Lexical and Dense Retrieval for Computationally Efficient Multi-hop Question Answering (Sidiropoulos et al., sustainlp 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.sustainlp-1.7.pdf
Video:
 https://aclanthology.org/2021.sustainlp-1.7.mp4
Code
 gsidiropoulos/hybrid_retrieval_for_efficient_qa
Data
HotpotQA