{"id":23430727,"url":"https://github.com/iesl/dilated-cnn-ner","last_synced_at":"2025-10-27T19:32:54.381Z","repository":{"id":39228989,"uuid":"87519235","full_name":"iesl/dilated-cnn-ner","owner":"iesl","description":"Dilated CNNs for NER in TensorFlow","archived":false,"fork":false,"pushed_at":"2019-03-09T01:04:42.000Z","size":164,"stargazers_count":242,"open_issues_count":7,"forks_count":58,"subscribers_count":22,"default_branch":"master","last_synced_at":"2025-03-31T08:44:09.632Z","etag":null,"topics":["cnns","machine-learning","named-entity-recognition","natural-language-processing","neural-networks","tensorflow"],"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/iesl.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}},"created_at":"2017-04-07T07:44:11.000Z","updated_at":"2025-01-17T09:52:43.000Z","dependencies_parsed_at":"2022-09-07T10:40:10.270Z","dependency_job_id":null,"html_url":"https://github.com/iesl/dilated-cnn-ner","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/iesl%2Fdilated-cnn-ner","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iesl%2Fdilated-cnn-ner/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iesl%2Fdilated-cnn-ner/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iesl%2Fdilated-cnn-ner/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/iesl","download_url":"https://codeload.github.com/iesl/dilated-cnn-ner/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252853023,"owners_count":21814444,"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":["cnns","machine-learning","named-entity-recognition","natural-language-processing","neural-networks","tensorflow"],"created_at":"2024-12-23T09:46:43.982Z","updated_at":"2025-10-27T19:32:54.290Z","avatar_url":"https://github.com/iesl.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# dilated-cnn-ner\n\nThis code implements the models described in the paper\n\"[Fast and Accurate Entity Recognition with Iterated Dilated Convolutions](https://arxiv.org/abs/1702.02098)\"\nby [Emma Strubell](https://cs.umass.edu/~strubell), [Patrick Verga](https://cs.umass.edu/~pat),\n[David Belanger](https://cs.umass.edu/~belanger) and [Andrew McCallum](https://cs.umass.edu/~mccallum).\n\nRequirements\n-----\nThis code uses TensorFlow v[1.0, 1.4) and Python 2.7.\n\nIt will probably train on a CPU, but honestly we haven't tried, and highly recommend training on a GPU.\n\n\nSetup\n-----\n1. Set up environment variables. For example, from the root directory of this project:\n\n  ```\n  export DILATED_CNN_NER_ROOT=`pwd`\n  export DATA_DIR=/path/to/conll-2003\n  ```\n\n2. Get some pretrained word embeddings, e.g. [SENNA embeddings](http://ronan.collobert.com/senna/download.html) or\n  [Glove embeddings](https://nlp.stanford.edu/projects/glove/). The code expects a space-separated file\n  with one word and its embedding per line, e.g.:\n   ```\n   word 0.45 0.67 0.99 ...\n   ```\n   Make a directory for the embeddings:\n   ```\n   mkdir -p data/embeddings\n   ```\n   and place the file there.\n\n3. Perform all data preprocessing for a given configuration. For example:\n\n  ```\n  ./bin/preprocess.sh conf/conll/dilated-cnn.conf\n  ```\n\n  This calls `preprocess.py`, which loads the data from text files, maps the tokens, labels and any other features to\n  integers, and writes to TensorFlow tfrecords.\n\nTraining\n----\nOnce the data preprocessing is completed, you can train a tagger:\n\n  ```\n  ./bin/train-cnn.sh conf/conll/dilated-cnn.conf\n  ```\n\nEvaluation\n----\nBy default, the trainer will write the model which achieved the best dev F1. To evaluate a saved model on the dev set:\n\n  ```\n  ./bin/eval-cnn.sh conf/conll/dilated-cnn.conf --load_model path/to/model\n  ```\nTo evaluate a saved model on the test set:\n\n  ```\n  ./bin/eval-cnn.sh conf/conll/dilated-cnn.conf test --load_model path/to/model\n  ```\n\n\nConfigs\n----\nConfiguration files (`conf/*`) specify all the data, parameters, etc. for an experiment.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fiesl%2Fdilated-cnn-ner","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fiesl%2Fdilated-cnn-ner","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fiesl%2Fdilated-cnn-ner/lists"}