{"id":19085049,"url":"https://github.com/jaywalnut310/label-propagation-with-seq2seq","last_synced_at":"2026-05-24T04:30:17.284Z","repository":{"id":85847229,"uuid":"96265464","full_name":"jaywalnut310/Label-Propagation-with-Seq2Seq","owner":"jaywalnut310","description":"Label-Propagation-with-Seq2Seq","archived":false,"fork":false,"pushed_at":"2017-08-03T07:13:19.000Z","size":4471,"stargazers_count":0,"open_issues_count":0,"forks_count":4,"subscribers_count":4,"default_branch":"master","last_synced_at":"2025-01-02T21:38:12.526Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/jaywalnut310.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2017-07-05T01:42:43.000Z","updated_at":"2017-07-27T02:27:28.000Z","dependencies_parsed_at":"2023-03-08T16:45:40.940Z","dependency_job_id":null,"html_url":"https://github.com/jaywalnut310/Label-Propagation-with-Seq2Seq","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/jaywalnut310%2FLabel-Propagation-with-Seq2Seq","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jaywalnut310%2FLabel-Propagation-with-Seq2Seq/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jaywalnut310%2FLabel-Propagation-with-Seq2Seq/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jaywalnut310%2FLabel-Propagation-with-Seq2Seq/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jaywalnut310","download_url":"https://codeload.github.com/jaywalnut310/Label-Propagation-with-Seq2Seq/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":240136988,"owners_count":19753645,"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":[],"created_at":"2024-11-09T02:53:37.690Z","updated_at":"2026-05-24T04:30:17.189Z","avatar_url":"https://github.com/jaywalnut310.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Label-Propagation with Seq2Seq\n\n## 0. Introduction\n\nThis project implements label propagation with seq2seq.\nIt applies [Neural Graph Machines](https://arxiv.org/abs/1703.04818) to Seq2Seq.\n\n### Problem Settings\n\n* Semi-supervised learning techniques such as label propagation are used to solve classification (finite-categories) problems.\n* And these approaches produce improvements at some extent.\n* However, these approaches are not applied well to solve continuous target (infinite-categories) problems. \n* Therefore, I want to tackle this problem using Neural Graph Machines in this project.\n\n\n### Some Details\n\n* I test the performance in Neural Machine Translation problem.\n* For calculating distance between nodes, I use L1, L2, and Mahalanobis distance metrics.\n* Presentation info is given in https://goo.gl/whAbB1\n\n----\n\n### You can explore the whole project code by following jupyter notebook codes.\n\n\u003e **toy_example.ipynb** : contruct 2D sinc function with biased parallel data and unbiased non-parallel data\n\n\u003e **preprocessing.ipynb** : preprocess sentences\n\n\u003e **graph_operations.ipynb** : construct graph from source sentences\n\n\u003e **neural_graph_machines-benchmark.ipynb** : Default Encoder-Attention-Decoder Neural Translation Model\n\n\u003e **neural_graph_machines.ipynb** : Neural Graph Machine Model\n\n\n## 1. Data Preparation\n\nExperiments are done with IWSLT English-Vietnamese data set.\n\nYou can download using **download.sh**\n\nI also use monolingual data from http://www.manythings.org/anki/.\n\nAfter that, run **preprocessing.ipynb**\n\n## 2. Graph Construction\n\nrun **graph_operations.ipynb**\n\n## 3. Experiments\n\nrun **neural_graph_machines-benchmark.ipynb** and **neural_graph_machines.ipynb**","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjaywalnut310%2Flabel-propagation-with-seq2seq","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjaywalnut310%2Flabel-propagation-with-seq2seq","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjaywalnut310%2Flabel-propagation-with-seq2seq/lists"}