@inproceedings{sun-etal-2024-apollo-optimized,
title = "{APOLLO}: An Optimized Training Approach for Long-form Numerical Reasoning",
author = "Sun, Jiashuo and
Zhang, Hang and
Lin, Chen and
Su, Xiangdong and
Gong, Yeyun and
Guo, Jian",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.122",
pages = "1370--1382",
abstract = "Long-form numerical reasoning aims to generate a reasoning program to calculate the answer for a given question. Previous work followed a retriever-generator framework, where the retriever selects key facts from a long-form document, and the generator generates a reasoning program based on the retrieved facts. However, they treated all facts equally without considering the different contributions of facts with and without numerical information. Furthermore, they ignored program consistency, leading to the wrong punishment of programs that differed from the ground truth. In order to address these issues, we proposed APOLLO (An optimized training aPproach fOr Long-form numericaL reasOning), to improve long-form numerical reasoning. APOLLO includes a number-aware negative sampling strategy for the retriever to discriminate key numerical facts, and a consistency-based reinforcement learning with target program augmentation for the generator to ultimately increase the execution accuracy. Experimental results on the FinQA and ConvFinQA leaderboards verify the effectiveness of our proposed methods, achieving the new state-of-the-art.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sun-etal-2024-apollo-optimized">
<titleInfo>
<title>APOLLO: An Optimized Training Approach for Long-form Numerical Reasoning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiashuo</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hang</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiangdong</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yeyun</namePart>
<namePart type="family">Gong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jian</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Long-form numerical reasoning aims to generate a reasoning program to calculate the answer for a given question. Previous work followed a retriever-generator framework, where the retriever selects key facts from a long-form document, and the generator generates a reasoning program based on the retrieved facts. However, they treated all facts equally without considering the different contributions of facts with and without numerical information. Furthermore, they ignored program consistency, leading to the wrong punishment of programs that differed from the ground truth. In order to address these issues, we proposed APOLLO (An optimized training aPproach fOr Long-form numericaL reasOning), to improve long-form numerical reasoning. APOLLO includes a number-aware negative sampling strategy for the retriever to discriminate key numerical facts, and a consistency-based reinforcement learning with target program augmentation for the generator to ultimately increase the execution accuracy. Experimental results on the FinQA and ConvFinQA leaderboards verify the effectiveness of our proposed methods, achieving the new state-of-the-art.</abstract>
<identifier type="citekey">sun-etal-2024-apollo-optimized</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.122</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>1370</start>
<end>1382</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T APOLLO: An Optimized Training Approach for Long-form Numerical Reasoning
%A Sun, Jiashuo
%A Zhang, Hang
%A Lin, Chen
%A Su, Xiangdong
%A Gong, Yeyun
%A Guo, Jian
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F sun-etal-2024-apollo-optimized
%X Long-form numerical reasoning aims to generate a reasoning program to calculate the answer for a given question. Previous work followed a retriever-generator framework, where the retriever selects key facts from a long-form document, and the generator generates a reasoning program based on the retrieved facts. However, they treated all facts equally without considering the different contributions of facts with and without numerical information. Furthermore, they ignored program consistency, leading to the wrong punishment of programs that differed from the ground truth. In order to address these issues, we proposed APOLLO (An optimized training aPproach fOr Long-form numericaL reasOning), to improve long-form numerical reasoning. APOLLO includes a number-aware negative sampling strategy for the retriever to discriminate key numerical facts, and a consistency-based reinforcement learning with target program augmentation for the generator to ultimately increase the execution accuracy. Experimental results on the FinQA and ConvFinQA leaderboards verify the effectiveness of our proposed methods, achieving the new state-of-the-art.
%U https://aclanthology.org/2024.lrec-main.122
%P 1370-1382
Markdown (Informal)
[APOLLO: An Optimized Training Approach for Long-form Numerical Reasoning](https://aclanthology.org/2024.lrec-main.122) (Sun et al., LREC-COLING 2024)
ACL