{"id":29144402,"url":"https://github.com/lyh-yf/mwptoolkit","last_synced_at":"2025-10-08T17:14:58.090Z","repository":{"id":37534049,"uuid":"332998918","full_name":"LYH-YF/MWPToolkit","owner":"LYH-YF","description":"MWPToolkit is an open-source framework for math word problem(MWP) solvers.","archived":false,"fork":false,"pushed_at":"2022-09-28T02:20:32.000Z","size":62694,"stargazers_count":163,"open_issues_count":19,"forks_count":35,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-09-06T18:34:33.264Z","etag":null,"topics":["deep-learning","graph-to-tree","math-word-problem","pretrained-language-model","pytorch","sequence-to-sequence","sequence-to-tree"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/LYH-YF.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2021-01-26T06:58:29.000Z","updated_at":"2025-08-15T08:29:28.000Z","dependencies_parsed_at":"2022-08-08T20:30:59.276Z","dependency_job_id":null,"html_url":"https://github.com/LYH-YF/MWPToolkit","commit_stats":null,"previous_names":[],"tags_count":3,"template":false,"template_full_name":null,"purl":"pkg:github/LYH-YF/MWPToolkit","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LYH-YF%2FMWPToolkit","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LYH-YF%2FMWPToolkit/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LYH-YF%2FMWPToolkit/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LYH-YF%2FMWPToolkit/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/LYH-YF","download_url":"https://codeload.github.com/LYH-YF/MWPToolkit/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LYH-YF%2FMWPToolkit/sbom","scorecard":{"id":81815,"data":{"date":"2025-08-11","repo":{"name":"github.com/LYH-YF/MWPToolkit","commit":"0993beb336c286a0f974d58834e932cf65e32249"},"scorecard":{"version":"v5.2.1-40-gf6ed084d","commit":"f6ed084d17c9236477efd66e5b258b9d4cc7b389"},"score":1.7,"checks":[{"name":"Code-Review","score":0,"reason":"Found 0/30 approved changesets -- score normalized to 0","details":null,"documentation":{"short":"Determines if the project requires human code review before pull requests (aka merge requests) are merged.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#code-review"}},{"name":"Packaging","score":-1,"reason":"packaging workflow not detected","details":["Warn: no GitHub/GitLab publishing workflow detected."],"documentation":{"short":"Determines if the project is published as a package that others can easily download, install, easily update, and uninstall.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#packaging"}},{"name":"Token-Permissions","score":-1,"reason":"No tokens found","details":null,"documentation":{"short":"Determines if the project's workflows follow the principle of least privilege.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#token-permissions"}},{"name":"Maintained","score":0,"reason":"0 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 0","details":null,"documentation":{"short":"Determines if the project is \"actively maintained\".","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#maintained"}},{"name":"Dangerous-Workflow","score":-1,"reason":"no workflows found","details":null,"documentation":{"short":"Determines if the project's GitHub Action workflows avoid dangerous patterns.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#dangerous-workflow"}},{"name":"SAST","score":0,"reason":"no SAST tool detected","details":["Warn: no pull requests merged into dev branch"],"documentation":{"short":"Determines if the project uses static code analysis.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#sast"}},{"name":"CII-Best-Practices","score":0,"reason":"no effort to earn an OpenSSF best practices badge detected","details":null,"documentation":{"short":"Determines if the project has an OpenSSF (formerly CII) Best Practices Badge.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#cii-best-practices"}},{"name":"Security-Policy","score":0,"reason":"security policy file not detected","details":["Warn: no security policy file detected","Warn: no security file to analyze","Warn: no security file to analyze","Warn: no security file to analyze"],"documentation":{"short":"Determines if the project has published a security policy.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#security-policy"}},{"name":"License","score":10,"reason":"license file detected","details":["Info: project has a license file: LICENSE:0","Info: FSF or OSI recognized license: MIT License: LICENSE:0"],"documentation":{"short":"Determines if the project has defined a license.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#license"}},{"name":"Fuzzing","score":0,"reason":"project is not fuzzed","details":["Warn: no fuzzer integrations found"],"documentation":{"short":"Determines if the project uses fuzzing.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#fuzzing"}},{"name":"Binary-Artifacts","score":10,"reason":"no binaries found in the repo","details":null,"documentation":{"short":"Determines if the project has generated executable (binary) artifacts in the source repository.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#binary-artifacts"}},{"name":"Signed-Releases","score":-1,"reason":"no releases found","details":null,"documentation":{"short":"Determines if the project cryptographically signs release artifacts.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#signed-releases"}},{"name":"Branch-Protection","score":0,"reason":"branch protection not enabled on development/release branches","details":["Warn: branch protection not enabled for branch 'master'"],"documentation":{"short":"Determines if the default and release branches are protected with GitHub's branch protection settings.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#branch-protection"}},{"name":"Vulnerabilities","score":0,"reason":"31 existing vulnerabilities detected","details":["Warn: Project is vulnerable to: PYSEC-2021-356 / GHSA-2ww3-fxvq-293j","Warn: Project is vulnerable to: PYSEC-2024-167 / GHSA-cgvx-9447-vcch","Warn: Project is vulnerable to: PYSEC-2021-859 / GHSA-f8m6-h2c7-8h9x","Warn: Project is vulnerable to: PYSEC-2022-5 / GHSA-rqjh-jp2r-59cj","Warn: Project is vulnerable to: GHSA-3pww-qvr8-6mhp","Warn: Project is vulnerable to: GHSA-6cxr-8q3m-jwrr","Warn: Project is vulnerable to: GHSA-h3xg-wv58-5p43","Warn: Project is vulnerable to: PYSEC-2025-23 / GHSA-w4rh-fgx7-q63m","Warn: Project is vulnerable to: GHSA-3749-ghw9-m3mg","Warn: Project is vulnerable to: PYSEC-2022-43015 / GHSA-47fc-vmwq-366v","Warn: Project is vulnerable to: PYSEC-2025-41 / GHSA-53q9-r3pm-6pq6","Warn: Project is vulnerable to: PYSEC-2024-252 / GHSA-5pcm-hx3q-hm94","Warn: Project is vulnerable to: GHSA-887c-mr87-cxwp","Warn: Project is vulnerable to: PYSEC-2024-251 / GHSA-pg7h-5qx3-wjr3","Warn: Project is vulnerable to: PYSEC-2024-250","Warn: Project is vulnerable to: PYSEC-2024-259","Warn: Project is vulnerable to: PYSEC-2023-299 / GHSA-282v-666c-3fvg","Warn: Project is vulnerable to: GHSA-37mw-44qp-f5jm","Warn: Project is vulnerable to: GHSA-37q5-v5qm-c9v8","Warn: Project is vulnerable to: PYSEC-2023-300 / GHSA-3863-2447-669p","Warn: Project is vulnerable to: GHSA-6rvg-6v2m-4j46","Warn: Project is vulnerable to: GHSA-9356-575x-2w9m","Warn: Project is vulnerable to: GHSA-fpwr-67px-3qhx","Warn: Project is vulnerable to: PYSEC-2024-229 / GHSA-hxxf-235m-72v3","Warn: Project is vulnerable to: GHSA-jjph-296x-mrcr","Warn: Project is vulnerable to: GHSA-phhr-52qp-3mj4","Warn: Project is vulnerable to: GHSA-q2wp-rjmx-x6x9","Warn: Project is vulnerable to: PYSEC-2025-40 / GHSA-qq3j-4f4f-9583","Warn: Project is vulnerable to: PYSEC-2024-227 / GHSA-qxrp-vhvm-j765","Warn: Project is vulnerable to: PYSEC-2023-301 / GHSA-v68g-wm8c-6x7j","Warn: Project is vulnerable to: PYSEC-2024-228 / GHSA-wrfc-pvp9-mr9g"],"documentation":{"short":"Determines if the project has open, known unfixed vulnerabilities.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#vulnerabilities"}},{"name":"Pinned-Dependencies","score":-1,"reason":"no dependencies found","details":null,"documentation":{"short":"Determines if the project has declared and pinned the dependencies of its build process.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#pinned-dependencies"}}]},"last_synced_at":"2025-08-15T06:03:58.429Z","repository_id":37534049,"created_at":"2025-08-15T06:03:58.429Z","updated_at":"2025-08-15T06:03:58.429Z"},"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":278981518,"owners_count":26079640,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-10-08T02:00:06.501Z","response_time":56,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["deep-learning","graph-to-tree","math-word-problem","pretrained-language-model","pytorch","sequence-to-sequence","sequence-to-tree"],"created_at":"2025-06-30T21:01:11.554Z","updated_at":"2025-10-08T17:14:58.084Z","avatar_url":"https://github.com/LYH-YF.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"![](https://github.com/LYH-YF/MWPToolkit/blob/master/title.png)\n\n##\n\n[![PyPi Latest Release](https://img.shields.io/pypi/v/mwptoolkit)](https://pypi.org/project/mwptoolkit/)\n[![License](https://img.shields.io/badge/License-MIT-blue.svg)](./LICENSE)\n[![Documentation Status](https://readthedocs.org/projects/mwptoolkit/badge/?version=latest)](https://mwptoolkit.readthedocs.io/en/latest/?badge=latest)\n\n[Doc](https://mwptoolkit.readthedocs.io/en/latest/)|[Model](#model)|[Dataset](#dataset)|[Paper](https://arxiv.org/pdf/2109.00799.pdf)\n\nMWPToolkit is a PyTorch-based toolkit for Math Word Problem (MWP) solving and has been accepted for publication in the AAAI 2022 demo track. It is a comprehensive framework for research purpose that integrates popular MWP benchmark datasets and typical deep learning-based MWP algorithms. \n\nOur framework has the following architecture. You could utilize our toolkit to evaluate the build-in datasets, apply it to process your raw data copies or develop your own models. \n\n![](https://github.com/LYH-YF/MWPToolkit/blob/master/architecture1.png)\n\u003cdiv align=\"center\"\u003e Figure: The Overall Framework of MWP Toolkit \u003c/div\u003e\n\n\n\n## News in version 0.0.7\n\n* 1.Fix some bugs [Issue #18]\n* 2.New dataset APE200k\n\n\n## News in version 0.0.6\n\n* 1.Fix some bugs [Issue [#12](https://github.com/LYH-YF/MWPToolkit/issues/12), [#8](https://github.com/LYH-YF/MWPToolkit/issues/8)]:\n\n  (1)**from_prefix_to_infix**,**from_postfix_to_infix** in mwptoolkit/utils/preprocess_tool/equation_operator.py\n\n  (2)the sequence length will be longer than pos_embedder's max length in **RobertGen**, **BertGen**.\n  \n  (3)data preprocessing for new dataset won't **automatically remove 'x=' or '=x'** in single equation.\n\n* 2.Update new models:\n\n  (1)Seq2Tree model [**BertTD**](https://arxiv.org/abs/2110.08464)\n\n  (2)Seq2Tree model [**MWPBert**](https://arxiv.org/abs/2107.13435)\n* 3.Rewrite Dataloader and Config\n\n* 4.Implement function save_dataset() and load_from_pretrained() of Dataset\n\n* 5.Implement function save_config() and load_from_pretrained() of Config\n\n## Characteristics\n\n* **Unification and Modularization**. We decouple solvers with different model architectures into highly modularized, reusable components and integrate them in a unified framework, which includes data, model, evaluation modules. It is convenient for you to study MWPs at a conceptual level and compare different models fairly.\n* **Comprehensiveness and Standardization**. MWPToolkit has deployed the popular benchmark datasets and models for MWPs solving, covering Seq2Seq, Seq2Tree, Graph2Tree, and Pre-trained Language Models. Moreover, some tricks like hyper-parameter tuning used in general NLP tasks are integrated. As all models can be implemented with a same experimental configuration, the evaluation of different models is standardized.\n* **Extensibility and Usability**. MWPToolkit provides user-friendly interfaces for various functions or modules. And the components in the pipeline architecture are modeled as exchangeable modules. You can try different combinations of modules via simply changing the configuration file or command line. You can also easily develop your own models by replacing or extending corresponding modules with your proposed ones.\n\n## Installation\nDevelopment environment:\n```\npython \u003e= 3.6.0\npytorch \u003e= 1.5.0\npyltp \u003e= 0.2.1 (optional)\n```\n\n### Method 1: Install from pip\n\n```\npip install mwptoolkit\n```\n### Method 2: Install from source\n\n```\n# Clone current repo\ngit clone https://github.com/LYH-YF/MWPToolkit.git \u0026\u0026 cd MWPToolkit\n\n# Requirements\npip install -r requirements.txt\n```\n\n## Quick Start\n\n### Evaluate a build-in dataset with a model\n\nTo have an initial trial of our toolkit, you can use the provided cmd script:\n\n```\npython run_mwptoolkit.py --model=GTS --dataset=math23k --task_type=single_equation --equation_fix=prefix --k_fold=5 --test_step=5 --gpu_id=0\n```\n\nAbove script will run [GTS](https://www.ijcai.org/proceedings/2019/736) model on [Math23K](https://aclanthology.org/D17-1088/) dataset with 5 [cross-validation](https://en.wikipedia.org/wiki/Cross-validation_(statistics)#k-fold_cross-validation). It will take around **xx** minutes to train 5 GTS models independently and output the average scores of equation accuracy and value accuracy. The training log can be found in the [log file](https://github.com/LYH-YF/MWPToolkit/tree/master/log). \n\nIf you would like to change the parameters, such as ```dataset``` and ```model```, please refer to the following instruction: \n\n* ```model```: The model name you specify to apply. You can see all options in Section [Model](#model).\n* ```dataset```: The dataset name you specify to evaluate. You can see all options in Section [Dataset](#dataset).\n* ```task_type```: The type of generated equation. It should be chosen from options [single_equation | multi_equation]. Usually, it's up to the datasets. You can refer to [dataset](#dataset). The single-equation dataset corresponds to 'single_equation' in code and multiple-equation dataset corresponds 'multi_equation' in code.\n* ```equation_fix```: The type of equation generation order. It should be chosen from options [infix | postfix | prefix]. Please note some models require a specific type of equation generation order. Usually, the corresponding paper for model will mention which order it takes. You can look up the reference paper in Section [Model](#model).\n* ```k_fold```: The fold number of cross-validation. It could be either NA value or an integer. If it is NA value, it will run train-valid-test split procedure. \n* ```test_step```: The epoch number of training after which conducts the evaluation on test. It should be an interger.\n* ```gpu_id```: The GPU ID for training the model. It should be an integer based on your GPU configuration. Please note that we haven't tested the framework with multiple GPUs yet.\n\nPlease note ```model```, ```dataset``` and ```task_type``` are the required. We also provide the [interface](https://mwptoolkit.readthedocs.io/en/latest/_static/cmd.html) where you can config your experiments by clicking options and we automatically generate corresponding cmd lines. \n\n### Evaluate a new dataset\n\nOur supported datasets are all saved under the folder ```'dataset'```. Besides trying our code with these build-in datasets, we also provide the option for you to run models on your own data copies, you can follow the steps below:\n\n\u003cstrong\u003eStep 1\u003c/strong\u003e: Organize your dataset. Your dataset folder (same as the dataset name) should include three json files for train, validation and test, respectively: \n\n```\ndataset_name\n    |----trainset.json\n    |----validset.json\n    |----testset.json\n```\n\nMove your dataset folder under path ```'dataset'``` of our framework, the file structure would be like:\n\n```\ndataset\n    |----dataset_name\n            |----trainset.json\n            |----validset.json\n            |----testset.json\n```\n\n\u003cstrong\u003eStep 2\u003c/strong\u003e: Setup your dataset configuration. The dataset configuration files are saved under path ```'mwptoolkit/properties/dataset/'```. You can write your own dataset configuration and save a JSON file under the path. The path to your JSON file should be ```mwptoolkit/properties/dataset/dataset_name.json```\n\n\u003cstrong\u003eStep 3\u003c/strong\u003e: Run the code!\n\n```\npython run_mwptoolkit.py --model=[model_name] --dataset=[dataset_name] --task_type=[single_equation|multi_equation] --equation_fix=[infix|postfix|prefix] --k_fold=[5|None] --gpu_id=0\n```\n\nInstead of moving your dataset folder and dataset configuration file to the above folders, the following parameters can be set directly.\n\n* ```dataset_path```: The path to dataset folder. The default value is ```'dataset/dataset_name'```, you can change it to your own dataset path via appending ```--dataset_path=[your_dataset]``` to cmd script.\n* ```dataset_config_path```: The path to dataset configuration file. The default value is ```'mwptoolkit/properties/dataset/dataset_name.json'```, you can change it to your own dataset configuration path via appending ```--dataset_config_path=[your_dataset_configuration]``` to cmd script.\n\n### Run hyper-parameters search\n\nOur toolkit also provides the option to do hyper-parameters search, which could facilitate users to obtain optimal hyper-parameters efficiently. We integrated hyper-parameter search in our framework via ```ray.tune```. Due to the search procedure, it will take longer time to train a model.\n\nYou can run the cmd script template below:\n\n```\npython run_hyper_search.py --model=[model_name] --dataset=[dataset_name] --task_type=[single_equation|multi_equation] --equation_fix=[infix|postfix|prefix] --k_fold=[5|None] --cpu_per_trial=2 --gpu_per_trial=0.5 --samples=1 --search_file=search_file.json --gpu_id=0\n```\n\n* ```cpu_per_trial```: The CPU resources to allocate per trial.\n* ```gpu_per_trial```: The GPU resources to allocate per trial.\n* ```samples```: The number of sampling times from the search space.\n* ```search_file```: A json file including search parameter name and space. For example:```[\"embedding_size=[64,128,256]\",\"hidden_size=[256,512]\",\"learning_rate=(1e-4, 1e-2)\"]```\n* ```search_parameter```: If you don't have the search file, you can set this parameter in command line to specify the search space. For example:```--search_parameter=hidden_size=[256,512] --search_parameter=embedding_size=[64,128,256] --search_parameter=learning_rate='(1e-4, 1e-2)```.\n\n## Architecture\n\nWe have shown the overall architecture of our toolkit in the above [Figure](#news). The configuration is specified via command line, external config files and internal config dictionaries. Multiple processors and dataloaders are integrated to process different forms of data. Models and evaluators take charge of doing the training and evaluation. Therefore, input datasets will get prepared and trained based on the specified configuration. You can refer to [documentation]() for more information. \n\n### Dataset\n\nWe have deployed **8** popular MWP datasets in our toolkit. These datasets are divided into two categories, **Single-equation** dataset and **Multiple-equation** dataset, which can be found in the table below. We will keep updating more datasets like ape200k\u003ca href=\"https://arxiv.org/abs/2009.11506\"\u003e(Zhao et al., 2020)\u003c/a\u003e, dolphin1878\u003ca href=\"https://aclanthology.org/D15-1135/\"\u003e(Shi et al., 2015)\u003c/a\u003e and dolphin18k\u003ca href=\"https://aclanthology.org/P16-1084/\"\u003e(Huang et al., 2016)\u003c/a\u003e. \n\n\u003ctable align=\"center\"\u003e\n    \u003cthread align=\"center\"\u003e\n        \u003ctr\u003e\n            \u003cth align=\"center\"\u003etask\u003c/th\u003e\n            \u003cth align=\"center\"\u003edataset\u003c/th\u003e\n            \u003cth align=\"center\"\u003ereference\u003c/th\u003e\n        \u003c/tr\u003e\n    \u003c/thread\u003e\n    \u003ctbody align=\"center\"\u003e\n        \u003ctr\u003e\n            \u003ctd rowspan=\"4\" align=\"center\"\u003eSingle-equation dataset\u003c/td\u003e\n            \u003ctd align=\"center\"\u003emath23k\u003c/td\u003e\n            \u003ctd align=\"center\"\u003e\u003ca href=\"https://aclanthology.org/D17-1088/\"\u003e(Wang et al., 2017)\u003c/a\u003e\u003c/td\u003e\n        \u003c/tr\u003e\n        \u003ctr\u003e\n            \u003ctd align=\"center\"\u003easdiv-a\u003c/td\u003e\n            \u003ctd align=\"center\"\u003e\u003ca href=\"https://aclanthology.org/2020.acl-main.92/\"\u003e(Miao et al., 2020)\u003c/a\u003e\u003c/td\u003e\n        \u003c/tr\u003e\n        \u003ctr\u003e\n            \u003ctd align=\"center\"\u003emawps-single\u003c/td\u003e\n            \u003ctd align=\"center\"\u003e\u003ca href=\"https://aclanthology.org/N16-1136/\"\u003e(Kedziorski et al., 2016)\u003c/a\u003e\u003c/td\u003e\n        \u003c/tr\u003e\n        \u003ctr\u003e\n            \u003ctd align=\"center\"\u003emawps_asdiv-a_svamp\u003c/td\u003e\n            \u003ctd align=\"center\"\u003e\u003ca href=\"https://arxiv.org/abs/2103.07191\"\u003e(Patel et al., 2021)\u003c/a\u003e\u003c/td\u003e\n        \u003c/tr\u003e\n        \u003ctr\u003e\n            \u003ctd rowspan=\"4\" align=\"center\"\u003eMultiple-equation dataset\u003c/td\u003e\n            \u003ctd align=\"center\"\u003ealg514\u003c/td\u003e\n            \u003ctd align=\"center\"\u003e\u003ca href=\"https://aclanthology.org/P14-1026/\"\u003e(Kushman et al., 2014)\u003c/a\u003e\u003c/td\u003e\n        \u003c/tr\u003e\n        \u003ctr\u003e\n            \u003ctd align=\"center\"\u003edraw\u003c/td\u003e\n            \u003ctd align=\"center\"\u003e\u003ca href=\"https://arxiv.org/abs/1609.07197\"\u003e(Upadhyay et al., 2017)\u003c/a\u003e\u003c/td\u003e\n        \u003c/tr\u003e\n        \u003ctr\u003e\n            \u003ctd align=\"center\"\u003emawps\u003c/td\u003e\n            \u003ctd align=\"center\"\u003e\u003ca href=\"https://aclanthology.org/N16-1136/\"\u003e(Kedziorski et al., 2016)\u003c/a\u003e\u003c/td\u003e\n        \u003c/tr\u003e\n        \u003ctr\u003e\n            \u003ctd align=\"center\"\u003ehmwp\u003c/td\u003e\n            \u003ctd align=\"center\"\u003e\u003ca href=\"https://arxiv.org/abs/2010.06823\"\u003e(Qin et al., 2020)\u003c/a\u003e\u003c/td\u003e\n        \u003c/tr\u003e\n    \u003c/tbody\u003e\n\u003c/table\u003e\n\n### Model\n\nWe have deployed **18** deep learning MWP models in our toolkit. Based on the featured generation procedure, we categorize them into **Sequence-to-sequence**, **Sequence-to-tree**, **Graph-to-tree**, **VAE** and **Pre-trained** models. Please note Pre-trained models are simple implementation of pretrained language models on MWP solving task. The table is displayed as follows:\n\n\u003ctable align=\"center\"\u003e\n    \u003cthread\u003e\n        \u003ctr\u003e\n            \u003cth align=\"center\"\u003etype\u003c/th\u003e\n            \u003cth align=\"center\"\u003emodel\u003c/th\u003e\n            \u003cth align=\"center\"\u003ereference\u003c/th\u003e\n        \u003c/tr\u003e\n    \u003c/thread\u003e\n    \u003ctbody\u003e\n        \u003ctr\u003e\n            \u003ctd rowspan=\"7\"\u003eSeq2Seq\u003c/td\u003e\n            \u003ctd\u003eDNS\u003c/td\u003e\n            \u003ctd align=\"center\"\u003e\u003ca href=\"https://aclanthology.org/D17-1088/\"\u003e(Wang et al., 2017)\u003c/a\u003e\u003c/td\u003e\n        \u003c/tr\u003e\n        \u003ctr\u003e\n            \u003ctd\u003eMathEN\u003c/td\u003e\n            \u003ctd align=\"center\"\u003e\u003ca href=\"https://aclanthology.org/D18-1132/\"\u003e(Wang et al., 2018)\u003c/a\u003e\u003c/td\u003e\n        \u003c/tr\u003e\n        \u003ctr\u003e\n            \u003ctd\u003eSaligned\u003c/td\u003e\n            \u003ctd align=\"center\"\u003e\u003ca href=\"https://aclanthology.org/N19-1272/\"\u003e(Chiang et al., 2019)\u003c/a\u003e\u003c/td\u003e\n        \u003c/tr\u003e\n        \u003ctr\u003e\n            \u003ctd\u003eGroupATT\u003c/td\u003e\n            \u003ctd align=\"center\"\u003e\u003ca href=\"https://aclanthology.org/P19-1619/\"\u003e(Li et al., 2019)\u003c/a\u003e\u003c/td\u003e\n        \u003c/tr\u003e\n        \u003ctr\u003e\n            \u003ctd\u003eRNN\u003c/td\u003e\n            \u003ctd align=\"center\"\u003e\u003ca href=\"https://arxiv.org/abs/1409.3215\"\u003e(Sutskever et al., 2014)\u003c/a\u003e\u003c/td\u003e\n        \u003c/tr\u003e\n        \u003ctr\u003e\n            \u003ctd\u003eRNNVAE\u003c/td\u003e\n            \u003ctd align=\"center\"\u003e\u003ca href=\"https://arxiv.org/abs/1605.07869\"\u003e(Zhang et al., 2016)\u003c/a\u003e\u003c/td\u003e\n        \u003c/tr\u003e\n        \u003ctr\u003e\n            \u003ctd\u003eTransformer\u003c/td\u003e\n            \u003ctd align=\"center\"\u003e\u003ca href=\"https://arxiv.org/abs/1706.03762\"\u003e(Vaswani et al., 2017)\u003c/a\u003e\u003c/td\u003e\n        \u003c/tr\u003e\n        \u003ctr\u003e\n            \u003ctd rowspan=\"7\"\u003eSeq2Tree\u003c/td\u003e\n            \u003ctd\u003eTRNN\u003c/td\u003e\n            \u003ctd align=\"center\"\u003e\u003ca href=\"https://ojs.aaai.org//index.php/AAAI/article/view/4697\"\u003e(Wang et al., 2019)\u003c/a\u003e\u003c/td\u003e\n        \u003c/tr\u003e\n        \u003ctr\u003e\n            \u003ctd\u003eAST-Dec\u003c/td\u003e\n            \u003ctd align=\"center\"\u003e\u003ca href=\"https://aclanthology.org/D19-1241/\"\u003e(Liu et al., 2019)\u003c/a\u003e\u003c/td\u003e\n        \u003c/tr\u003e\n        \u003ctr\u003e\n            \u003ctd\u003eGTS\u003c/td\u003e\n            \u003ctd align=\"center\"\u003e\u003ca href=\"https://www.ijcai.org/proceedings/2019/736\"\u003e(Xie et al., 2019)\u003c/a\u003e\u003c/td\u003e\n        \u003c/tr\u003e\n        \u003ctr\u003e\n            \u003ctd\u003eSAUSolver\u003c/td\u003e\n            \u003ctd align=\"center\"\u003e\u003ca href=\"https://arxiv.org/abs/2010.06823\"\u003e(Qin et al., 2020)\u003c/a\u003e\u003c/td\u003e\n        \u003c/tr\u003e\n        \u003ctr\u003e\n            \u003ctd\u003eTSN\u003c/td\u003e\n            \u003ctd align=\"center\"\u003e\u003ca href=\"https://www.ijcai.org/proceedings/2020/555\"\u003e(Zhang et al., 2020)\u003c/a\u003e\u003c/td\u003e\n        \u003c/tr\u003e\n        \u003ctr\u003e\n            \u003ctd\u003eBertTD\u003c/td\u003e\n            \u003ctd align=\"center\"\u003e\u003ca href=\"https://arxiv.org/abs/2110.08464\"\u003e(Li et al., 2021)\u003c/a\u003e\u003c/td\u003e\n        \u003c/tr\u003e\n        \u003ctr\u003e\n            \u003ctd\u003eMWPBert\u003c/td\u003e\n            \u003ctd align=\"center\"\u003e\u003ca href=\"https://arxiv.org/abs/2107.13435\"\u003e(Liang et al., 2021)\u003c/a\u003e\u003c/td\u003e\n        \u003c/tr\u003e\n        \u003ctr\u003e\n            \u003ctd rowspan=\"2\"\u003eGraph2Tree\u003c/td\u003e\n            \u003ctd\u003eGraph2Tree\u003c/td\u003e\n            \u003ctd align=\"center\"\u003e\u003ca href=\"https://aclanthology.org/2020.acl-main.362/\"\u003e(Zhang et al., 2020)\u003c/a\u003e\u003c/td\u003e\n        \u003c/tr\u003e\n        \u003ctr\u003e\n            \u003ctd\u003eMultiE\u0026D\u003c/td\u003e\n            \u003ctd align=\"center\"\u003e\u003ca href=\"https://aclanthology.org/2020.coling-main.262/\"\u003e(Shen et al., 2020)\u003c/a\u003e\u003c/td\u003e\n        \u003c/tr\u003e\n        \u003ctr\u003e\n            \u003ctd rowspan=\"3\"\u003ePre-trained\u003c/td\u003e\n            \u003ctd\u003eBertGen\u003c/td\u003e\n            \u003ctd align=\"center\"\u003e\u003ca href=\"https://arxiv.org/abs/1810.04805\"\u003e(Devlin et al., 2018)\u003c/a\u003e\u003c/td\u003e\n        \u003c/tr\u003e\n        \u003ctr\u003e\n            \u003ctd\u003eRobertaGen\u003c/td\u003e\n            \u003ctd align=\"center\"\u003e\u003ca href=\"https://arxiv.org/abs/1907.11692\"\u003e(Liu et al., 2019)\u003c/a\u003e\u003c/td\u003e\n        \u003c/tr\u003e\n        \u003ctr\u003e\n            \u003ctd\u003eGPT-2\u003c/td\u003e\n            \u003ctd align=\"center\"\u003e\u003ca href=\"https://cdn.openai.com/better-language-models/language_models_are_unsupervised_multitask_learners.pdf\"\u003e(Radford et al., 2019)\u003c/a\u003e\u003c/td\u003e\n        \u003c/tr\u003e\n    \u003c/tbody\u003e\n\u003c/table\u003e\n\n\n### Evaluation metric\n\nWe have implemented 2 evaluation metrics to measure the effect of MWP models. \n\n\u003ctable align=\"center\"\u003e\n    \u003cthread\u003e\n        \u003ctr\u003e\n            \u003cth align=\"center\"\u003emeasurement\u003c/th\u003e\n            \u003cth align=\"center\"\u003enote\u003c/th\u003e\n        \u003c/tr\u003e\n    \u003c/thread\u003e\n    \u003ctbody\u003e\n        \u003ctr\u003e\n            \u003ctd\u003eEqu acc\u003c/td\u003e\n            \u003ctd align=\"center\"\u003eThe predicted equation is exactly match the correct equation\n        \u003c/tr\u003e\n        \u003ctr\u003e\n            \u003ctd\u003eVal acc\u003c/td\u003e\n            \u003ctd align=\"center\"\u003eThe predicted answer is match the correct answer\n        \u003c/tr\u003e\n    \u003c/tbody\u003e\n\u003c/table\u003e\n\n## Experiment Results\n\nWe have implemented the models on the datasets that are integrated within our toolkit. All the implementation follows the build-in configurations. All the experiments are conducted with 5 cross-validation. The experiment results(Equ acc|Val acc) are displayed in the following table.\n\n### \u003cdiv align=\"center\"\u003eSingle-equation Task Results\u003c/div\u003e\n\u003ctable align=\"center\"\u003e\n    \u003ctr\u003e\n        \u003cth rowspan=\"3\"\u003emodel\u003c/th\u003e\n        \u003ctd align=\"center\" colspan=\"8\"\u003e\u003cstrong\u003eDataset\u003c/strong\u003e\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003cth colspan=\"2\"\u003emath23k\u003c/th\u003e\n        \u003cth colspan=\"2\"\u003emawps-single\u003c/th\u003e\n        \u003cth colspan=\"2\"\u003easdiv-a\u003c/th\u003e\n        \u003cth colspan=\"2\"\u003emawps_asdiv-a_svamp\u003c/th\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003cth\u003eEqu. Acc\u003c/th\u003e\n        \u003cth\u003eAns. Acc\u003c/th\u003e\n        \u003cth\u003eEqu. Acc\u003c/th\u003e\n        \u003cth\u003eAns. Acc\u003c/th\u003e\n        \u003cth\u003eEqu. Acc\u003c/th\u003e\n        \u003cth\u003eAns. Acc\u003c/th\u003e\n        \u003cth\u003eEqu. Acc\u003c/th\u003e\n        \u003cth\u003eAns. Acc\u003c/th\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003ctd\u003eDNS\u003c/td\u003e\n        \u003ctd\u003e57.1\u003c/td\u003e\n        \u003ctd\u003e67.5\u003c/td\u003e\n        \u003ctd\u003e78.9\u003c/td\u003e\n        \u003ctd\u003e86.3\u003c/td\u003e\n        \u003ctd\u003e63.0\u003c/td\u003e\n        \u003ctd\u003e66.2\u003c/td\u003e\n        \u003ctd\u003e22.1\u003c/td\u003e\n        \u003ctd\u003e24.2\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003ctd\u003eMathEN\u003c/td\u003e\n        \u003ctd\u003e66.7\u003c/td\u003e\n        \u003ctd\u003e69.5\u003c/td\u003e\n        \u003ctd\u003e85.9\u003c/td\u003e\n        \u003ctd\u003e86.4\u003c/td\u003e\n        \u003ctd\u003e64.3\u003c/td\u003e\n        \u003ctd\u003e64.7\u003c/td\u003e\n        \u003ctd\u003e21.8\u003c/td\u003e\n        \u003ctd\u003e25.0\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003ctd\u003eSaligned\u003c/td\u003e\n        \u003ctd\u003e59.1\u003c/td\u003e\n        \u003ctd\u003e69.0\u003c/td\u003e\n        \u003ctd\u003e86.0\u003c/td\u003e\n        \u003ctd\u003e86.3\u003c/td\u003e\n        \u003ctd\u003e66.0\u003c/td\u003e\n        \u003ctd\u003e67.9\u003c/td\u003e\n        \u003ctd\u003e23.9\u003c/td\u003e\n        \u003ctd\u003e26.1\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003ctd\u003eGroupATT\u003c/td\u003e\n        \u003ctd\u003e56.7\u003c/td\u003e\n        \u003ctd\u003e66.6\u003c/td\u003e\n        \u003ctd\u003e84.7\u003c/td\u003e\n        \u003ctd\u003e85.3\u003c/td\u003e\n        \u003ctd\u003e59.5\u003c/td\u003e\n        \u003ctd\u003e61.0\u003c/td\u003e\n        \u003ctd\u003e19.2\u003c/td\u003e\n        \u003ctd\u003e21.5\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003ctd\u003eAttSeq\u003c/td\u003e\n        \u003ctd\u003e57.1\u003c/td\u003e\n        \u003ctd\u003e68.7\u003c/td\u003e\n        \u003ctd\u003e79.4\u003c/td\u003e\n        \u003ctd\u003e87.0\u003c/td\u003e\n        \u003ctd\u003e64.2\u003c/td\u003e\n        \u003ctd\u003e68.3\u003c/td\u003e\n        \u003ctd\u003e23.0\u003c/td\u003e\n        \u003ctd\u003e25.4\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003ctd\u003eLSTMVAE\u003c/td\u003e\n        \u003ctd\u003e59.0\u003c/td\u003e\n        \u003ctd\u003e70.0\u003c/td\u003e\n        \u003ctd\u003e79.8\u003c/td\u003e\n        \u003ctd\u003e88.2\u003c/td\u003e\n        \u003ctd\u003e64.0\u003c/td\u003e\n        \u003ctd\u003e68.7\u003c/td\u003e\n        \u003ctd\u003e23.2\u003c/td\u003e\n        \u003ctd\u003e25.9\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003ctd\u003eTransformer\u003c/td\u003e\n        \u003ctd\u003e52.3\u003c/td\u003e\n        \u003ctd\u003e61.5\u003c/td\u003e\n        \u003ctd\u003e77.9\u003c/td\u003e\n        \u003ctd\u003e85.6\u003c/td\u003e\n        \u003ctd\u003e57.2\u003c/td\u003e\n        \u003ctd\u003e59.3\u003c/td\u003e\n        \u003ctd\u003e18.4\u003c/td\u003e\n        \u003ctd\u003e20.7\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003ctd\u003eTRNN\u003c/td\u003e\n        \u003ctd\u003e65.0\u003c/td\u003e\n        \u003ctd\u003e68.1\u003c/td\u003e\n        \u003ctd\u003e86.0\u003c/td\u003e\n        \u003ctd\u003e86.5\u003c/td\u003e\n        \u003ctd\u003e68.9\u003c/td\u003e\n        \u003ctd\u003e69.3\u003c/td\u003e\n        \u003ctd\u003e22.6\u003c/td\u003e\n        \u003ctd\u003e26.1\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003ctd\u003eAST-Dec\u003c/td\u003e\n        \u003ctd\u003e57.5\u003c/td\u003e\n        \u003ctd\u003e67.7\u003c/td\u003e\n        \u003ctd\u003e84.1\u003c/td\u003e\n        \u003ctd\u003e84.8\u003c/td\u003e\n        \u003ctd\u003e54.5\u003c/td\u003e\n        \u003ctd\u003e56.0\u003c/td\u003e\n        \u003ctd\u003e21.9\u003c/td\u003e\n        \u003ctd\u003e24.7\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003ctd\u003eGTS\u003c/td\u003e\n        \u003ctd\u003e63.4\u003c/td\u003e\n        \u003ctd\u003e74.2\u003c/td\u003e\n        \u003ctd\u003e83.5\u003c/td\u003e\n        \u003ctd\u003e84.1\u003c/td\u003e\n        \u003ctd\u003e67.7\u003c/td\u003e\n        \u003ctd\u003e69.9\u003c/td\u003e\n        \u003ctd\u003e25.6\u003c/td\u003e\n        \u003ctd\u003e29.1\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003ctd\u003eSAU-Solver\u003c/td\u003e\n        \u003ctd\u003e64.6\u003c/td\u003e\n        \u003ctd\u003e75.1\u003c/td\u003e\n        \u003ctd\u003e83.4\u003c/td\u003e\n        \u003ctd\u003e84.0\u003c/td\u003e\n        \u003ctd\u003e68.5\u003c/td\u003e\n        \u003ctd\u003e71.2\u003c/td\u003e\n        \u003ctd\u003e27.1\u003c/td\u003e\n        \u003ctd\u003e29.7\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003ctd\u003eTSN\u003c/td\u003e\n        \u003ctd\u003e63.8\u003c/td\u003e\n        \u003ctd\u003e74.4\u003c/td\u003e\n        \u003ctd\u003e84.0\u003c/td\u003e\n        \u003ctd\u003e84.7\u003c/td\u003e\n        \u003ctd\u003e68.5\u003c/td\u003e\n        \u003ctd\u003e71.0\u003c/td\u003e\n        \u003ctd\u003e25.7\u003c/td\u003e\n        \u003ctd\u003e29.0\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003ctd\u003eGraph2Tree\u003c/td\u003e\n        \u003ctd\u003e64.9\u003c/td\u003e\n        \u003ctd\u003e75.3\u003c/td\u003e\n        \u003ctd\u003e84.9\u003c/td\u003e\n        \u003ctd\u003e85.6\u003c/td\u003e\n        \u003ctd\u003e72.4\u003c/td\u003e\n        \u003ctd\u003e75.3\u003c/td\u003e\n        \u003ctd\u003e31.6\u003c/td\u003e\n        \u003ctd\u003e35.0\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003ctd\u003eMultiE\u0026D\u003c/td\u003e\n        \u003ctd\u003e65.5\u003c/td\u003e\n        \u003ctd\u003e76.5\u003c/td\u003e\n        \u003ctd\u003e83.2\u003c/td\u003e\n        \u003ctd\u003e84.1\u003c/td\u003e\n        \u003ctd\u003e70.5\u003c/td\u003e\n        \u003ctd\u003e72.6\u003c/td\u003e\n        \u003ctd\u003e29.3\u003c/td\u003e\n        \u003ctd\u003e32.4\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003ctd\u003eMWPBert\u003c/td\u003e\n        \u003ctd\u003e70.9\u003c/td\u003e\n        \u003ctd\u003e82.5\u003c/td\u003e\n        \u003ctd\u003e-\u003c/td\u003e\n        \u003ctd\u003e-\u003c/td\u003e\n        \u003ctd\u003e-\u003c/td\u003e\n        \u003ctd\u003e-\u003c/td\u003e\n        \u003ctd\u003e-\u003c/td\u003e\n        \u003ctd\u003e-\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003ctd\u003eBERTGen\u003c/td\u003e\n        \u003ctd\u003e64.8\u003c/td\u003e\n        \u003ctd\u003e76.6\u003c/td\u003e\n        \u003ctd\u003e79.0\u003c/td\u003e\n        \u003ctd\u003e86.9\u003c/td\u003e\n        \u003ctd\u003e68.7\u003c/td\u003e\n        \u003ctd\u003e71.5\u003c/td\u003e\n        \u003ctd\u003e22.2\u003c/td\u003e\n        \u003ctd\u003e24.8\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003ctd\u003eRoBERTaGen\u003c/td\u003e\n        \u003ctd\u003e65.2\u003c/td\u003e\n        \u003ctd\u003e76.9\u003c/td\u003e\n        \u003ctd\u003e80.8\u003c/td\u003e\n        \u003ctd\u003e88.4\u003c/td\u003e\n        \u003ctd\u003e68.7\u003c/td\u003e\n        \u003ctd\u003e72.1\u003c/td\u003e\n        \u003ctd\u003e27.9\u003c/td\u003e\n        \u003ctd\u003e30.3\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003ctd\u003eGPT-2\u003c/td\u003e\n        \u003ctd\u003e63.8\u003c/td\u003e\n        \u003ctd\u003e74.3\u003c/td\u003e\n        \u003ctd\u003e75.4\u003c/td\u003e\n        \u003ctd\u003e75.9\u003c/td\u003e\n        \u003ctd\u003e59.9\u003c/td\u003e\n        \u003ctd\u003e61.4\u003c/td\u003e\n        \u003ctd\u003e22.5\u003c/td\u003e\n        \u003ctd\u003e25.7\u003c/td\u003e\n    \u003c/tr\u003e\n\u003c/table\u003e\n\n### \u003cdiv align=\"center\"\u003eMultiple-equation Task Result\u003c/div\u003e\n\u003ctable align=\"center\"\u003e\n    \u003ctr\u003e\n        \u003cth rowspan=\"3\"\u003emodel\u003c/th\u003e\n        \u003ctd align=\"center\" colspan=\"6\"\u003e\u003cstrong\u003eDataset\u003c/strong\u003e\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003cth colspan=\"2\"\u003edraw\u003c/th\u003e\n        \u003cth colspan=\"2\"\u003ehmwp\u003c/th\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003cth\u003eEqu. Acc\u003c/th\u003e\n        \u003cth\u003eAns. Acc\u003c/th\u003e\n        \u003cth\u003eEqu. Acc\u003c/th\u003e\n        \u003cth\u003eAns. Acc\u003c/th\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003ctd\u003eDNS\u003c/td\u003e\n        \u003ctd\u003e35.8\u003c/td\u003e\n        \u003ctd\u003e36.8\u003c/td\u003e\n        \u003ctd\u003e24.0\u003c/td\u003e\n        \u003ctd\u003e32.7\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003ctd\u003eMathEN\u003c/td\u003e\n        \u003ctd\u003e38.2\u003c/td\u003e\n        \u003ctd\u003e39.5\u003c/td\u003e\n        \u003ctd\u003e32.4\u003c/td\u003e\n        \u003ctd\u003e43.7\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003ctd\u003eSaligned\u003c/td\u003e\n        \u003ctd\u003e36.7\u003c/td\u003e\n        \u003ctd\u003e37.8\u003c/td\u003e\n        \u003ctd\u003e31.0\u003c/td\u003e\n        \u003ctd\u003e41.8\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003ctd\u003eGroupATT\u003c/td\u003e\n        \u003ctd\u003e30.4\u003c/td\u003e\n        \u003ctd\u003e31.4\u003c/td\u003e\n        \u003ctd\u003e25.2\u003c/td\u003e\n        \u003ctd\u003e33.2\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003ctd\u003eAttSeq\u003c/td\u003e\n        \u003ctd\u003e39.7\u003c/td\u003e\n        \u003ctd\u003e41.2\u003c/td\u003e\n        \u003ctd\u003e32.9\u003c/td\u003e\n        \u003ctd\u003e44.7\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003ctd\u003eLSTMVAE\u003c/td\u003e\n        \u003ctd\u003e40.9\u003c/td\u003e\n        \u003ctd\u003e42.3\u003c/td\u003e\n        \u003ctd\u003e33.6\u003c/td\u003e\n        \u003ctd\u003e45.9\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003ctd\u003eTransformer\u003c/td\u003e\n        \u003ctd\u003e27.1\u003c/td\u003e\n        \u003ctd\u003e28.3\u003c/td\u003e\n        \u003ctd\u003e24.4\u003c/td\u003e\n        \u003ctd\u003e32.4\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003ctd\u003eTRNN\u003c/td\u003e\n        \u003ctd\u003e27.4\u003c/td\u003e\n        \u003ctd\u003e28.9\u003c/td\u003e\n        \u003ctd\u003e27.2\u003c/td\u003e\n        \u003ctd\u003e36.8\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003ctd\u003eAST-Dec\u003c/td\u003e\n        \u003ctd\u003e26.0\u003c/td\u003e\n        \u003ctd\u003e26.7\u003c/td\u003e\n        \u003ctd\u003e24.9\u003c/td\u003e\n        \u003ctd\u003e32.0\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003ctd\u003eGTS\u003c/td\u003e\n        \u003ctd\u003e38.6\u003c/td\u003e\n        \u003ctd\u003e39.9\u003c/td\u003e\n        \u003ctd\u003e33.7\u003c/td\u003e\n        \u003ctd\u003e44.6\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003ctd\u003eSAU-Solver\u003c/td\u003e\n        \u003ctd\u003e38.4\u003c/td\u003e\n        \u003ctd\u003e39.2\u003c/td\u003e\n        \u003ctd\u003e33.1\u003c/td\u003e\n        \u003ctd\u003e43.7\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003ctd\u003eTSN\u003c/td\u003e\n        \u003ctd\u003e39.3\u003c/td\u003e\n        \u003ctd\u003e40.4\u003c/td\u003e\n        \u003ctd\u003e34.3\u003c/td\u003e\n        \u003ctd\u003e44.9\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003ctd\u003eGraph2Tree\u003c/td\u003e\n        \u003ctd\u003e39.8\u003c/td\u003e\n        \u003ctd\u003e41.0\u003c/td\u003e\n        \u003ctd\u003e34.4\u003c/td\u003e\n        \u003ctd\u003e45.1\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003ctd\u003eMultiE\u0026D\u003c/td\u003e\n        \u003ctd\u003e38.1\u003c/td\u003e\n        \u003ctd\u003e39.2\u003c/td\u003e\n        \u003ctd\u003e34.6\u003c/td\u003e\n        \u003ctd\u003e45.3\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003ctd\u003eMWPBert\u003c/td\u003e\n        \u003ctd\u003e-\u003c/td\u003e\n        \u003ctd\u003e-\u003c/td\u003e\n        \u003ctd\u003e-\u003c/td\u003e\n        \u003ctd\u003e-\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003ctd\u003eBERTGen\u003c/td\u003e\n        \u003ctd\u003e33.9\u003c/td\u003e\n        \u003ctd\u003e35.0\u003c/td\u003e\n        \u003ctd\u003e29.2\u003c/td\u003e\n        \u003ctd\u003e39.5\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003ctd\u003eRoBERTaGen\u003c/td\u003e\n        \u003ctd\u003e34.2\u003c/td\u003e\n        \u003ctd\u003e34.9\u003c/td\u003e\n        \u003ctd\u003e30.6\u003c/td\u003e\n        \u003ctd\u003e41.0\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003ctd\u003eGPT-2\u003c/td\u003e\n        \u003ctd\u003e30.7\u003c/td\u003e\n        \u003ctd\u003e31.5\u003c/td\u003e\n        \u003ctd\u003e36.3\u003c/td\u003e\n        \u003ctd\u003e49.0\u003c/td\u003e\n    \u003c/tr\u003e\n\u003c/table\u003e\n## Contributing\n\nWe will keep updating and maintaining this repository. You are welcome to contribute to this repository through giving us suggestions and developing extensions! If you have any questions or encounter a bug, please fill an [issue](https://github.com/LYH-YF/MWPToolkit/issues). \n\n## Cite\n\nIf you find MWP toolkit is useful for your research, please cite:\n\n```\n@article{lan2021mwptoolkit,\n    title={MWPToolkit: An Open-Source Framework for Deep Learning-Based Math Word Problem Solvers},\n    author={Yihuai Lan and Lei Wang and Qiyuan Zhang and Yunshi Lan and Bing Tian Dai and Yan Wang and Dongxiang Zhang and Ee-Peng Lim},\n    journal={arXiv preprint arXiv:2109.00799},\n    year={2021}\n}\n```\n\n\n## License\n\nMWPToolkit uses [MIT License](https://github.com/LYH-YF/MWPToolkit/blob/master/LICENSE).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flyh-yf%2Fmwptoolkit","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flyh-yf%2Fmwptoolkit","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flyh-yf%2Fmwptoolkit/lists"}