{"id":20580620,"url":"https://github.com/pmhalvor/mtl-tsa","last_synced_at":"2026-04-10T21:38:44.369Z","repository":{"id":200455306,"uuid":"468735879","full_name":"pmhalvor/mtl-tsa","owner":"pmhalvor","description":"Multitask Learning for Targeted Sentiment Analysis using Transformer-Based Models","archived":false,"fork":false,"pushed_at":"2022-03-11T18:02:38.000Z","size":257,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-01-16T22:33:50.597Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/pmhalvor.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}},"created_at":"2022-03-11T12:07:24.000Z","updated_at":"2022-10-12T05:51:28.000Z","dependencies_parsed_at":"2023-10-17T01:24:44.344Z","dependency_job_id":"9042f958-ac27-401c-8580-742406a7b41a","html_url":"https://github.com/pmhalvor/mtl-tsa","commit_stats":null,"previous_names":["pmhalvor/mtl-tsa"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pmhalvor%2Fmtl-tsa","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pmhalvor%2Fmtl-tsa/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pmhalvor%2Fmtl-tsa/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pmhalvor%2Fmtl-tsa/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/pmhalvor","download_url":"https://codeload.github.com/pmhalvor/mtl-tsa/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":242206045,"owners_count":20089255,"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":"2024-11-16T06:24:35.053Z","updated_at":"2026-04-10T21:38:39.348Z","avatar_url":"https://github.com/pmhalvor.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"## Targeted Sentiment Analysis for Norwegian\n\nThis repository provides the data, baseline code, and extras necessary to begin work on the targeted sentiment track for IN5550. Cloning this repo is meant as a quick way of getting something working, but there are many ways of improving these results, ranging from small technical changes (including a hyperparameter search, more/less regularization, small architecture modifications) to larger and more theoretical changes (Comparing model architectures, adding character-level information, or using transfer learning models). Feel free to change anything necessary in the code.\n\n## Usage\n\n```\npython baseline.py --NUM_LAYERS number of hidden layers for BiLSTM \\\\\n                   --HIDDEN_DIM dimensionality of LSTM layers \\\\\n                   --BATCH_SIZE number of examples to include in a batch \\\\\n                   --DROPOUT dropout to be applied after embedding layer \\\\\n                   --EMBEDDING_DIM dimensionality of embeddings \\\\\n                   --EMBEDDINGS location of pretrained embeddings \\\\\n                   --TRAIN_EMBEDDINGS whether to train or leave fixed \\\\\n                   --LEARNING_RATE learning rate for ADAM optimizer \\\\\n                   --EPOCHS number of epochs to train model\n```\n\nNote that with the current code, you have to provide the model with pretrained embeddings. All other parameters can be left as default values.\n\n## Requirements\n\n1. Python 3\n2. sklearn  ```pip install -U scikit-learn```\n3. Pytorch ```pip install torch torchvision torchtext```\n4. tqdm ```pip install tqdm```\n5. torchtext ```pip install torchtext```\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpmhalvor%2Fmtl-tsa","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpmhalvor%2Fmtl-tsa","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpmhalvor%2Fmtl-tsa/lists"}