Dense Retrieval as Indirect Supervision for Large-space Decision Making

Nan Xu, Fei Wang, Mingtao Dong, Muhao Chen


Abstract
Many discriminative natural language understanding (NLU) tasks have large label spaces. Learning such a process of large-space decision making is particularly challenging due to the lack of training instances per label and the difficulty of selection among many fine-grained labels. Inspired by dense retrieval methods for passage finding in open-domain QA, we propose a reformulation of large-space discriminative NLU tasks as a learning-to-retrieve task, leading to a novel solution named Dense Decision Retrieval (DDR). Instead of predicting fine-grained decisions as logits, DDR adopts a dual-encoder architecture that learns to predict by retrieving from a decision thesaurus. This approach not only leverages rich indirect supervision signals from easy-to-consume learning resources for dense retrieval, it also leads to enhanced prediction generalizability with a semantically meaningful representation of the large decision space. When evaluated on tasks with decision spaces ranging from hundreds to hundred-thousand scales, DDR outperforms strong baselines greatly by 27.54% in P @1 on two extreme multi-label classification tasks, 1.17% in F1 score ultra-fine entity typing, and 1.26% in accuracy on three few-shot intent classification tasks on average.
Anthology ID:
2023.findings-emnlp.1002
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
15021–15033
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.1002
DOI:
10.18653/v1/2023.findings-emnlp.1002
Bibkey:
Cite (ACL):
Nan Xu, Fei Wang, Mingtao Dong, and Muhao Chen. 2023. Dense Retrieval as Indirect Supervision for Large-space Decision Making. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 15021–15033, Singapore. Association for Computational Linguistics.
Cite (Informal):
Dense Retrieval as Indirect Supervision for Large-space Decision Making (Xu et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-emnlp.1002.pdf