@inproceedings{xu-etal-2023-dense,
title = "Dense Retrieval as Indirect Supervision for Large-space Decision Making",
author = "Xu, Nan and
Wang, Fei and
Dong, Mingtao and
Chen, Muhao",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.1002",
doi = "10.18653/v1/2023.findings-emnlp.1002",
pages = "15021--15033",
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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2023-dense">
<titleInfo>
<title>Dense Retrieval as Indirect Supervision for Large-space Decision Making</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nan</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingtao</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhao</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">xu-etal-2023-dense</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.1002</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.1002</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>15021</start>
<end>15033</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dense Retrieval as Indirect Supervision for Large-space Decision Making
%A Xu, Nan
%A Wang, Fei
%A Dong, Mingtao
%A Chen, Muhao
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F xu-etal-2023-dense
%X 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.
%R 10.18653/v1/2023.findings-emnlp.1002
%U https://aclanthology.org/2023.findings-emnlp.1002
%U https://doi.org/10.18653/v1/2023.findings-emnlp.1002
%P 15021-15033
Markdown (Informal)
[Dense Retrieval as Indirect Supervision for Large-space Decision Making](https://aclanthology.org/2023.findings-emnlp.1002) (Xu et al., Findings 2023)
ACL