{"id":13628062,"url":"https://github.com/linmx0130/parserChiang","last_synced_at":"2025-04-17T00:33:10.952Z","repository":{"id":146515700,"uuid":"112438524","full_name":"linmx0130/parserChiang","owner":"linmx0130","description":"Naïve transition-based dependency parser in Gluon","archived":false,"fork":false,"pushed_at":"2019-10-17T07:52:21.000Z","size":58,"stargazers_count":6,"open_issues_count":0,"forks_count":0,"subscribers_count":3,"default_branch":"master","last_synced_at":"2024-11-08T18:46:09.657Z","etag":null,"topics":["conll-u","dependency-parser","gluon","mxnet","parser"],"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/linmx0130.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,"governance":null,"roadmap":null,"authors":null}},"created_at":"2017-11-29T06:53:40.000Z","updated_at":"2023-09-05T14:27:36.000Z","dependencies_parsed_at":"2023-04-12T14:30:38.648Z","dependency_job_id":null,"html_url":"https://github.com/linmx0130/parserChiang","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/linmx0130%2FparserChiang","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/linmx0130%2FparserChiang/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/linmx0130%2FparserChiang/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/linmx0130%2FparserChiang/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/linmx0130","download_url":"https://codeload.github.com/linmx0130/parserChiang/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":249293166,"owners_count":21245690,"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","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":["conll-u","dependency-parser","gluon","mxnet","parser"],"created_at":"2024-08-01T22:00:44.160Z","updated_at":"2025-04-17T00:33:10.671Z","avatar_url":"https://github.com/linmx0130.png","language":"Python","funding_links":[],"categories":["\u003ca name=\"NLP\"\u003e\u003c/a\u003e3. NLP"],"sub_categories":["2.14 Misc"],"readme":"parserChiang - Naïve Transition-based Dependency Parser in Gluon\n=====\nThis repo support CoNLL format, which is adapted by [Universal Dependencies](http://universaldependencies.org/) Project. parserChiang is implemented with great [MXNet gluon](http://gluon.mxnet.io/).\n\n![Babel Towel: right bottom part](https://upload.wikimedia.org/wikipedia/commons/thumb/9/9e/Pieter_Bruegel_the_Elder_-_The_Tower_of_Babel_%28Vienna%29_-_Google_Art_Project-x2-y1.jpg/600px-Pieter_Bruegel_the_Elder_-_The_Tower_of_Babel_%28Vienna%29_-_Google_Art_Project-x2-y1.jpg)\n### Models\nThere are different models in this repo:\n1. [DEPRECATED] *default/*: The default parser model using only word features. It is the baseline of all other models.\n2. [DEPRECATED] *pos_aid/*: This parser model requires standard POS tagging during inference, which is provided in CoNLL dataset. In practice, you may use Stanford NLP tools to get good POS tags.\n3. [DEPRECATED] *pos_joint/*: This parser model will predict POS tags. \n4. *pos_deprel_joint/*: This parser model will predict POS tags and **dependent relation label**. LAS index requires the output from this model. \n5. [DEPRECATED] *pos_aid_deprel_joint/*: This parser model requires standard POS tagging during inference, and will predict ependent relation label.\n\nThe models marked with [DEPRECATED] will not be updated to latest functions.\n\n### Usage\nData should be put into *data/* directory. Train the model with\n\u003cpre\u003e\n$ python3 train_pos_parser.py\n\u003c/pre\u003e\nIf the training procedure runs on GPU and the loss value become NaN abruptly, change to CPU training with following command:\n\u003cpre\u003e\n$ python3 train_pos_parser.py --cpu\n\u003c/pre\u003e\nThe maintainer is still working on this bug.\n\nThen it will create a directory named *model_dumps_{Date}_{Time}* to store the model dump. Test it with\n\u003cpre\u003e\n$ python3 test_pos_parser.py [model_path] [model_file]\n\u003c/pre\u003e\n\n### Notes\nThis implementation is a **low**-performance transition-based parser in both training speed and predicition accuracy. I created it as a toy model simply for learning natural language processing. **DO NOT USE IT IN ANY REAL WORLD TASKS**. \n\nHave fun with it!\n\n### License\nCopyright 2017-2019 Mengxiao Lin \\\u003clinmx0130@gmail.com\\\u003e, read LICENSE for more details.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flinmx0130%2FparserChiang","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flinmx0130%2FparserChiang","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flinmx0130%2FparserChiang/lists"}