@inproceedings{kessler-2025-dataset,
title = "A Dataset of {A}ncient {C}hinese Math Word Problems and an Application for Research in Historic Mathematics",
author = "Ke{\ss}ler, Florian",
editor = "Anderson, Adam and
Gordin, Shai and
Li, Bin and
Liu, Yudong and
Passarotti, Marco C. and
Sprugnoli, Rachele",
booktitle = "Proceedings of the Second Workshop on Ancient Language Processing",
month = may,
year = "2025",
address = "The Albuquerque Convention Center, Laguna",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.alp-1.8/",
doi = "10.18653/v1/2025.alp-1.8",
pages = "59--70",
ISBN = "979-8-89176-235-0",
abstract = "Solving math word problems, i.e. mathemati-cal problems stated in natural language, has re-ceived much attention in the Artificial Intelli-gence (AI) community over the last years. Un-surprisingly, research has focused on problems stated in contemporary languages. In contrast to this, in this article, we introduce a dataset of math word problems that is extracted from an-cient Chinese mathematical texts. The dataset is made available.1 We report a baseline per-formance for GPT-4o solving the problems in the dataset using a Program-of-Thought paradigm that translates the mathematical pro-cedures in the original texts into Python code, giving acceptable performance but showing that the model often struggles with understand-ing the pre-modern language. Finally, we de-scribe how the generated code can be used for research into the history of mathematics, by of-fering a way to search the texts by abstract op-erations instead of specific lexemes."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kessler-2025-dataset">
<titleInfo>
<title>A Dataset of Ancient Chinese Math Word Problems and an Application for Research in Historic Mathematics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Florian</namePart>
<namePart type="family">Keßler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Ancient Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Anderson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shai</namePart>
<namePart type="family">Gordin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yudong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="given">C</namePart>
<namePart type="family">Passarotti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachele</namePart>
<namePart type="family">Sprugnoli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">The Albuquerque Convention Center, Laguna</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-235-0</identifier>
</relatedItem>
<abstract>Solving math word problems, i.e. mathemati-cal problems stated in natural language, has re-ceived much attention in the Artificial Intelli-gence (AI) community over the last years. Un-surprisingly, research has focused on problems stated in contemporary languages. In contrast to this, in this article, we introduce a dataset of math word problems that is extracted from an-cient Chinese mathematical texts. The dataset is made available.1 We report a baseline per-formance for GPT-4o solving the problems in the dataset using a Program-of-Thought paradigm that translates the mathematical pro-cedures in the original texts into Python code, giving acceptable performance but showing that the model often struggles with understand-ing the pre-modern language. Finally, we de-scribe how the generated code can be used for research into the history of mathematics, by of-fering a way to search the texts by abstract op-erations instead of specific lexemes.</abstract>
<identifier type="citekey">kessler-2025-dataset</identifier>
<identifier type="doi">10.18653/v1/2025.alp-1.8</identifier>
<location>
<url>https://aclanthology.org/2025.alp-1.8/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>59</start>
<end>70</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Dataset of Ancient Chinese Math Word Problems and an Application for Research in Historic Mathematics
%A Keßler, Florian
%Y Anderson, Adam
%Y Gordin, Shai
%Y Li, Bin
%Y Liu, Yudong
%Y Passarotti, Marco C.
%Y Sprugnoli, Rachele
%S Proceedings of the Second Workshop on Ancient Language Processing
%D 2025
%8 May
%I Association for Computational Linguistics
%C The Albuquerque Convention Center, Laguna
%@ 979-8-89176-235-0
%F kessler-2025-dataset
%X Solving math word problems, i.e. mathemati-cal problems stated in natural language, has re-ceived much attention in the Artificial Intelli-gence (AI) community over the last years. Un-surprisingly, research has focused on problems stated in contemporary languages. In contrast to this, in this article, we introduce a dataset of math word problems that is extracted from an-cient Chinese mathematical texts. The dataset is made available.1 We report a baseline per-formance for GPT-4o solving the problems in the dataset using a Program-of-Thought paradigm that translates the mathematical pro-cedures in the original texts into Python code, giving acceptable performance but showing that the model often struggles with understand-ing the pre-modern language. Finally, we de-scribe how the generated code can be used for research into the history of mathematics, by of-fering a way to search the texts by abstract op-erations instead of specific lexemes.
%R 10.18653/v1/2025.alp-1.8
%U https://aclanthology.org/2025.alp-1.8/
%U https://doi.org/10.18653/v1/2025.alp-1.8
%P 59-70
Markdown (Informal)
[A Dataset of Ancient Chinese Math Word Problems and an Application for Research in Historic Mathematics](https://aclanthology.org/2025.alp-1.8/) (Keßler, ALP 2025)
ACL