@inproceedings{ki-etal-2020-generating,
title = "Generating Equation by Utilizing Operators : {GEO} model",
author = "Ki, Kyung Seo and
Lee, Donggeon and
Kim, Bugeun and
Gweon, Gahgene",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.38/",
doi = "10.18653/v1/2020.coling-main.38",
pages = "426--436",
abstract = "Math word problem solving is an emerging research topic in Natural Language Processing. Recently, to address the math word problem-solving task, researchers have applied the encoder-decoder architecture, which is mainly used in machine translation tasks. The state-of-the-art neural models use hand-crafted features and are based on generation methods. In this paper, we propose the GEO (Generation of Equations by utilizing Operators) model that does not use hand-crafted features and addresses two issues that are present in existing neural models: 1. missing domain-specific knowledge features and 2. losing encoder-level knowledge. To address missing domain-specific feature issue, we designed two auxiliary tasks: operation group difference prediction and implicit pair prediction. To address losing encoder-level knowledge issue, we added an Operation Feature Feed Forward (OP3F) layer. Experimental results showed that the GEO model outperformed existing state-of-the-art models on two datasets, 85.1{\%} in MAWPS, and 62.5{\%} in DRAW-1K, and reached comparable performance of 82.1{\%} in ALG514 dataset."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ki-etal-2020-generating">
<titleInfo>
<title>Generating Equation by Utilizing Operators : GEO model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kyung</namePart>
<namePart type="given">Seo</namePart>
<namePart type="family">Ki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Donggeon</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bugeun</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gahgene</namePart>
<namePart type="family">Gweon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Math word problem solving is an emerging research topic in Natural Language Processing. Recently, to address the math word problem-solving task, researchers have applied the encoder-decoder architecture, which is mainly used in machine translation tasks. The state-of-the-art neural models use hand-crafted features and are based on generation methods. In this paper, we propose the GEO (Generation of Equations by utilizing Operators) model that does not use hand-crafted features and addresses two issues that are present in existing neural models: 1. missing domain-specific knowledge features and 2. losing encoder-level knowledge. To address missing domain-specific feature issue, we designed two auxiliary tasks: operation group difference prediction and implicit pair prediction. To address losing encoder-level knowledge issue, we added an Operation Feature Feed Forward (OP3F) layer. Experimental results showed that the GEO model outperformed existing state-of-the-art models on two datasets, 85.1% in MAWPS, and 62.5% in DRAW-1K, and reached comparable performance of 82.1% in ALG514 dataset.</abstract>
<identifier type="citekey">ki-etal-2020-generating</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.38</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.38/</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>426</start>
<end>436</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generating Equation by Utilizing Operators : GEO model
%A Ki, Kyung Seo
%A Lee, Donggeon
%A Kim, Bugeun
%A Gweon, Gahgene
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F ki-etal-2020-generating
%X Math word problem solving is an emerging research topic in Natural Language Processing. Recently, to address the math word problem-solving task, researchers have applied the encoder-decoder architecture, which is mainly used in machine translation tasks. The state-of-the-art neural models use hand-crafted features and are based on generation methods. In this paper, we propose the GEO (Generation of Equations by utilizing Operators) model that does not use hand-crafted features and addresses two issues that are present in existing neural models: 1. missing domain-specific knowledge features and 2. losing encoder-level knowledge. To address missing domain-specific feature issue, we designed two auxiliary tasks: operation group difference prediction and implicit pair prediction. To address losing encoder-level knowledge issue, we added an Operation Feature Feed Forward (OP3F) layer. Experimental results showed that the GEO model outperformed existing state-of-the-art models on two datasets, 85.1% in MAWPS, and 62.5% in DRAW-1K, and reached comparable performance of 82.1% in ALG514 dataset.
%R 10.18653/v1/2020.coling-main.38
%U https://aclanthology.org/2020.coling-main.38/
%U https://doi.org/10.18653/v1/2020.coling-main.38
%P 426-436
Markdown (Informal)
[Generating Equation by Utilizing Operators : GEO model](https://aclanthology.org/2020.coling-main.38/) (Ki et al., COLING 2020)
ACL
- Kyung Seo Ki, Donggeon Lee, Bugeun Kim, and Gahgene Gweon. 2020. Generating Equation by Utilizing Operators : GEO model. In Proceedings of the 28th International Conference on Computational Linguistics, pages 426–436, Barcelona, Spain (Online). International Committee on Computational Linguistics.