{"id":15662354,"url":"https://github.com/naivehobo/hobonet","last_synced_at":"2025-05-05T23:24:42.348Z","repository":{"id":67884810,"uuid":"101106968","full_name":"naiveHobo/HoboNet","owner":"naiveHobo","description":"Convolution Neural Network for classification of semantic relations in a sentence","archived":false,"fork":false,"pushed_at":"2017-08-24T21:51:57.000Z","size":52489,"stargazers_count":17,"open_issues_count":1,"forks_count":6,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-03-31T00:41:17.410Z","etag":null,"topics":["embeddings-word2vec","natural-language-processing","natural-language-understanding","relation-classification","semeval","semeval-2018","semeval2014","sentence-classification","word2vec"],"latest_commit_sha":null,"homepage":"","language":"Python","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/naiveHobo.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":"2017-08-22T21:00:38.000Z","updated_at":"2025-01-20T10:31:31.000Z","dependencies_parsed_at":"2023-02-26T12:31:31.471Z","dependency_job_id":null,"html_url":"https://github.com/naiveHobo/HoboNet","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/naiveHobo%2FHoboNet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/naiveHobo%2FHoboNet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/naiveHobo%2FHoboNet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/naiveHobo%2FHoboNet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/naiveHobo","download_url":"https://codeload.github.com/naiveHobo/HoboNet/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252591547,"owners_count":21773128,"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":["embeddings-word2vec","natural-language-processing","natural-language-understanding","relation-classification","semeval","semeval-2018","semeval2014","sentence-classification","word2vec"],"created_at":"2024-10-03T13:32:03.525Z","updated_at":"2025-05-05T23:24:42.342Z","avatar_url":"https://github.com/naiveHobo.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# HoboNet - Relation Classification\nConvolution neural network for classification of semantic relationship between two given entities\n\n**Test accuracy: 80.06%**\n\n**Macro F1 score (excluding Other): 84.18%**\n\n#### Step 1:\nPrepare train.txt and text.txt run preprocess.py:\n```\npython preprocess.py\n```\n\n#### Step 2:\nTo get the vector representation of all the words, and then save them as a pickle.\n\nYou will need the embeddings we used: https://www.cs.york.ac.uk/nlp/extvec/wiki_extvec.gz\n\nDownload the .gz file and place it in a folder called 'embeddings'\n```\npython prepare_data.py\n```\nThe word embeddings, look-up table, training data and test data get saved into a pickle file in ./pkl\n\n#### Step 3:\nTo train the cnn model:\n```\npython train.py\n```\nAll the models are saved in ./model\n\n#### Step 4:\nTo view the results of the above step:\n```\npython test.py\n```\nIt will display the accuracy and the F1 score on the test dataset\n\n#### Step 5:\nTo use the official SemEval2010-Task8 Scorer:\n```\nperl scorer/semeval2010_task8_scorer-v1.2.pl results/HoboNet_result.txt scorer/test_key.txt \u003e scorer/result_scores.txt\n```\nThis will create result_scores.txt file that contains the official scores and confusion matrix for this task\n\n#### Dependencies:\n```\nNumPy\nKeras\ncPickle\ngzip\n\nUse python2\n```\n\n## References: \n\n- Pengda Qin, Weiran Xu, Jun Guo, An empirical convolutional neural network approach for semantic relation classification, Neurocomputing, Volume 190, 2016, Pages 1-9, ISSN 0925-2312, http://dx.doi.org/10.1016/j.neucom.2015.12.091\n- Ngoc Thang Vu, Heike Adel, Pankaj Gupta, Hinrich Schütze, Combining Recurrent and Convolutional Neural Networks for Relation Classification, arXiv:1605.07333 [cs.CL]\n- Cicero Nogueira dos Santos, Bing Xiang, Bowen Zhou, Classifying Relations by Ranking with Convolutional Neural Networks,  \tarXiv:1504.06580 [cs.CL]\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnaivehobo%2Fhobonet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fnaivehobo%2Fhobonet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnaivehobo%2Fhobonet/lists"}