{"id":13935791,"url":"https://github.com/hsinyuan-huang/FusionNet-NLI","last_synced_at":"2025-07-19T21:30:38.934Z","repository":{"id":83652565,"uuid":"114311097","full_name":"hsinyuan-huang/FusionNet-NLI","owner":"hsinyuan-huang","description":"An example for applying FusionNet to Natural Language Inference","archived":false,"fork":false,"pushed_at":"2018-12-10T20:40:50.000Z","size":23,"stargazers_count":135,"open_issues_count":5,"forks_count":39,"subscribers_count":9,"default_branch":"master","last_synced_at":"2024-11-27T03:34:37.010Z","etag":null,"topics":["deep-learning","machine-comprehension","nlp"],"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/hsinyuan-huang.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":"2017-12-15T00:55:36.000Z","updated_at":"2024-03-20T09:00:18.000Z","dependencies_parsed_at":"2023-03-12T07:00:44.355Z","dependency_job_id":null,"html_url":"https://github.com/hsinyuan-huang/FusionNet-NLI","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/hsinyuan-huang/FusionNet-NLI","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hsinyuan-huang%2FFusionNet-NLI","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hsinyuan-huang%2FFusionNet-NLI/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hsinyuan-huang%2FFusionNet-NLI/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hsinyuan-huang%2FFusionNet-NLI/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/hsinyuan-huang","download_url":"https://codeload.github.com/hsinyuan-huang/FusionNet-NLI/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hsinyuan-huang%2FFusionNet-NLI/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":266019657,"owners_count":23864916,"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":["deep-learning","machine-comprehension","nlp"],"created_at":"2024-08-07T23:02:05.841Z","updated_at":"2025-07-19T21:30:38.929Z","avatar_url":"https://github.com/hsinyuan-huang.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# FusionNet for Natural Language Inference\n\nThis is an example for applying FusionNet to natural language inference task.  \nFor more details on FusionNet, please refer to our paper:  \n[FusionNet: Fusing via Fully-Aware Attention with Application to Machine Comprehension](https://arxiv.org/abs/1711.07341)  \n\nRequirements\n------------\n+ Python (version 3.5.2)\n+ PyTorch (0.2.0)\n+ spaCy (1.x)\n+ NumPy\n+ JSON Lines\n+ MessagePack\n\nSince package update sometimes break backward compatibility, it is recommended to use Docker, which can be downloaded from [here](https://www.docker.com/community-edition#/download). To enable GPU, [nvidia-docker](https://github.com/NVIDIA/nvidia-docker) may also needs to be installed.  \n\nAfter setting up Docker, simply perform `docker pull momohuang/fusionnet-docker` to pull the docker file. Note that this may take some time to download. Then we can run the docker image through  \n`docker run -it momohuang/fusionnet-docker` (Only CPU)  \nor  \n`nvidia-docker run -it momohuang/fusionnet-docker` (GPU-enabled).  \n\nQuick Start\n-----------\n`pip install -r requirements.txt`  \n`bash download.sh`  \n`python prepro.py`  \n`python train.py`  \n  \n`train.py` supports an option `--full_att_type`, where  \n`--full_att_type 0`: standard attention  \n`--full_att_type 1`: fully-aware attention  \n`--full_att_type 2`: fully-aware multi-level attention  \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhsinyuan-huang%2FFusionNet-NLI","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhsinyuan-huang%2FFusionNet-NLI","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhsinyuan-huang%2FFusionNet-NLI/lists"}