├── IR_Classification_Utils.py ├── README.md ├── datasets └── 20NSshort │ ├── labels.txt │ ├── mapping_dict.pkl │ ├── test.csv │ ├── test_docnade.csv │ ├── test_lstm.csv │ ├── training.csv │ ├── training_docnade.csv │ ├── training_lstm.csv │ ├── validation.csv │ ├── validation_docnade.csv │ ├── validation_lstm.csv │ ├── vocab_docnade.vocab │ └── vocab_lstm.vocab ├── docnade_embeddings_ir_full_vocab └── 20NSshort ├── docnade_embeddings_ppl_full_vocab └── 20NSshort ├── model ├── 20NSshort_DocNADE_act_sigmoid_hidden_200_vocab_1448_lr_0.001_proj_False_deep_False_4_12_2018 │ ├── logs │ │ ├── events.out.tfevents.1543953536.ip-172-31-20-187 │ │ ├── events.out.tfevents.1543953618.ip-172-31-20-187 │ │ ├── reload_info_ppl.txt │ │ ├── topics_ppl_V.txt │ │ ├── topics_ppl_W.txt │ │ └── training_info.txt │ ├── model_ppl │ │ ├── checkpoint │ │ ├── model_ppl-1.data-00000-of-00001 │ │ ├── model_ppl-1.index │ │ └── model_ppl-1.meta │ └── params.json ├── __init__.py ├── data.py ├── data_lstm.py ├── evaluate.py ├── model_supervised.py └── model_supervised_lstm.py ├── preprocess.py ├── preprocess_data.py ├── requirements.txt ├── train_20NSshort_docnade_IR.sh ├── train_20NSshort_docnade_PPL.sh ├── train_20NSshort_docnade_lstm_IR.sh ├── train_20NSshort_docnade_lstm_PPL.sh ├── train_model.py └── train_model_lstm.py /IR_Classification_Utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pgcool/textTOvec/HEAD/IR_Classification_Utils.py -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pgcool/textTOvec/HEAD/README.md -------------------------------------------------------------------------------- /datasets/20NSshort/labels.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pgcool/textTOvec/HEAD/datasets/20NSshort/labels.txt -------------------------------------------------------------------------------- /datasets/20NSshort/mapping_dict.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pgcool/textTOvec/HEAD/datasets/20NSshort/mapping_dict.pkl -------------------------------------------------------------------------------- /datasets/20NSshort/test.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pgcool/textTOvec/HEAD/datasets/20NSshort/test.csv -------------------------------------------------------------------------------- /datasets/20NSshort/test_docnade.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pgcool/textTOvec/HEAD/datasets/20NSshort/test_docnade.csv -------------------------------------------------------------------------------- /datasets/20NSshort/test_lstm.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pgcool/textTOvec/HEAD/datasets/20NSshort/test_lstm.csv -------------------------------------------------------------------------------- /datasets/20NSshort/training.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pgcool/textTOvec/HEAD/datasets/20NSshort/training.csv -------------------------------------------------------------------------------- /datasets/20NSshort/training_docnade.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pgcool/textTOvec/HEAD/datasets/20NSshort/training_docnade.csv -------------------------------------------------------------------------------- /datasets/20NSshort/training_lstm.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pgcool/textTOvec/HEAD/datasets/20NSshort/training_lstm.csv -------------------------------------------------------------------------------- /datasets/20NSshort/validation.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pgcool/textTOvec/HEAD/datasets/20NSshort/validation.csv -------------------------------------------------------------------------------- /datasets/20NSshort/validation_docnade.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pgcool/textTOvec/HEAD/datasets/20NSshort/validation_docnade.csv -------------------------------------------------------------------------------- /datasets/20NSshort/validation_lstm.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pgcool/textTOvec/HEAD/datasets/20NSshort/validation_lstm.csv -------------------------------------------------------------------------------- /datasets/20NSshort/vocab_docnade.vocab: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pgcool/textTOvec/HEAD/datasets/20NSshort/vocab_docnade.vocab -------------------------------------------------------------------------------- /datasets/20NSshort/vocab_lstm.vocab: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pgcool/textTOvec/HEAD/datasets/20NSshort/vocab_lstm.vocab -------------------------------------------------------------------------------- /docnade_embeddings_ir_full_vocab/20NSshort: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pgcool/textTOvec/HEAD/docnade_embeddings_ir_full_vocab/20NSshort -------------------------------------------------------------------------------- /docnade_embeddings_ppl_full_vocab/20NSshort: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pgcool/textTOvec/HEAD/docnade_embeddings_ppl_full_vocab/20NSshort -------------------------------------------------------------------------------- /model/20NSshort_DocNADE_act_sigmoid_hidden_200_vocab_1448_lr_0.001_proj_False_deep_False_4_12_2018/logs/events.out.tfevents.1543953536.ip-172-31-20-187: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pgcool/textTOvec/HEAD/model/20NSshort_DocNADE_act_sigmoid_hidden_200_vocab_1448_lr_0.001_proj_False_deep_False_4_12_2018/logs/events.out.tfevents.1543953536.ip-172-31-20-187 -------------------------------------------------------------------------------- /model/20NSshort_DocNADE_act_sigmoid_hidden_200_vocab_1448_lr_0.001_proj_False_deep_False_4_12_2018/logs/events.out.tfevents.1543953618.ip-172-31-20-187: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pgcool/textTOvec/HEAD/model/20NSshort_DocNADE_act_sigmoid_hidden_200_vocab_1448_lr_0.001_proj_False_deep_False_4_12_2018/logs/events.out.tfevents.1543953618.ip-172-31-20-187 -------------------------------------------------------------------------------- /model/20NSshort_DocNADE_act_sigmoid_hidden_200_vocab_1448_lr_0.001_proj_False_deep_False_4_12_2018/logs/reload_info_ppl.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pgcool/textTOvec/HEAD/model/20NSshort_DocNADE_act_sigmoid_hidden_200_vocab_1448_lr_0.001_proj_False_deep_False_4_12_2018/logs/reload_info_ppl.txt -------------------------------------------------------------------------------- /model/20NSshort_DocNADE_act_sigmoid_hidden_200_vocab_1448_lr_0.001_proj_False_deep_False_4_12_2018/logs/topics_ppl_V.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pgcool/textTOvec/HEAD/model/20NSshort_DocNADE_act_sigmoid_hidden_200_vocab_1448_lr_0.001_proj_False_deep_False_4_12_2018/logs/topics_ppl_V.txt -------------------------------------------------------------------------------- /model/20NSshort_DocNADE_act_sigmoid_hidden_200_vocab_1448_lr_0.001_proj_False_deep_False_4_12_2018/logs/topics_ppl_W.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pgcool/textTOvec/HEAD/model/20NSshort_DocNADE_act_sigmoid_hidden_200_vocab_1448_lr_0.001_proj_False_deep_False_4_12_2018/logs/topics_ppl_W.txt -------------------------------------------------------------------------------- /model/20NSshort_DocNADE_act_sigmoid_hidden_200_vocab_1448_lr_0.001_proj_False_deep_False_4_12_2018/logs/training_info.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pgcool/textTOvec/HEAD/model/20NSshort_DocNADE_act_sigmoid_hidden_200_vocab_1448_lr_0.001_proj_False_deep_False_4_12_2018/logs/training_info.txt -------------------------------------------------------------------------------- /model/20NSshort_DocNADE_act_sigmoid_hidden_200_vocab_1448_lr_0.001_proj_False_deep_False_4_12_2018/model_ppl/checkpoint: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pgcool/textTOvec/HEAD/model/20NSshort_DocNADE_act_sigmoid_hidden_200_vocab_1448_lr_0.001_proj_False_deep_False_4_12_2018/model_ppl/checkpoint -------------------------------------------------------------------------------- /model/20NSshort_DocNADE_act_sigmoid_hidden_200_vocab_1448_lr_0.001_proj_False_deep_False_4_12_2018/model_ppl/model_ppl-1.data-00000-of-00001: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pgcool/textTOvec/HEAD/model/20NSshort_DocNADE_act_sigmoid_hidden_200_vocab_1448_lr_0.001_proj_False_deep_False_4_12_2018/model_ppl/model_ppl-1.data-00000-of-00001 -------------------------------------------------------------------------------- /model/20NSshort_DocNADE_act_sigmoid_hidden_200_vocab_1448_lr_0.001_proj_False_deep_False_4_12_2018/model_ppl/model_ppl-1.index: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pgcool/textTOvec/HEAD/model/20NSshort_DocNADE_act_sigmoid_hidden_200_vocab_1448_lr_0.001_proj_False_deep_False_4_12_2018/model_ppl/model_ppl-1.index -------------------------------------------------------------------------------- /model/20NSshort_DocNADE_act_sigmoid_hidden_200_vocab_1448_lr_0.001_proj_False_deep_False_4_12_2018/model_ppl/model_ppl-1.meta: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pgcool/textTOvec/HEAD/model/20NSshort_DocNADE_act_sigmoid_hidden_200_vocab_1448_lr_0.001_proj_False_deep_False_4_12_2018/model_ppl/model_ppl-1.meta -------------------------------------------------------------------------------- /model/20NSshort_DocNADE_act_sigmoid_hidden_200_vocab_1448_lr_0.001_proj_False_deep_False_4_12_2018/params.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pgcool/textTOvec/HEAD/model/20NSshort_DocNADE_act_sigmoid_hidden_200_vocab_1448_lr_0.001_proj_False_deep_False_4_12_2018/params.json -------------------------------------------------------------------------------- /model/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /model/data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pgcool/textTOvec/HEAD/model/data.py -------------------------------------------------------------------------------- /model/data_lstm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pgcool/textTOvec/HEAD/model/data_lstm.py -------------------------------------------------------------------------------- /model/evaluate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pgcool/textTOvec/HEAD/model/evaluate.py -------------------------------------------------------------------------------- /model/model_supervised.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pgcool/textTOvec/HEAD/model/model_supervised.py -------------------------------------------------------------------------------- /model/model_supervised_lstm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pgcool/textTOvec/HEAD/model/model_supervised_lstm.py -------------------------------------------------------------------------------- /preprocess.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pgcool/textTOvec/HEAD/preprocess.py -------------------------------------------------------------------------------- /preprocess_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pgcool/textTOvec/HEAD/preprocess_data.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pgcool/textTOvec/HEAD/requirements.txt -------------------------------------------------------------------------------- /train_20NSshort_docnade_IR.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pgcool/textTOvec/HEAD/train_20NSshort_docnade_IR.sh -------------------------------------------------------------------------------- /train_20NSshort_docnade_PPL.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pgcool/textTOvec/HEAD/train_20NSshort_docnade_PPL.sh -------------------------------------------------------------------------------- /train_20NSshort_docnade_lstm_IR.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pgcool/textTOvec/HEAD/train_20NSshort_docnade_lstm_IR.sh -------------------------------------------------------------------------------- /train_20NSshort_docnade_lstm_PPL.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pgcool/textTOvec/HEAD/train_20NSshort_docnade_lstm_PPL.sh -------------------------------------------------------------------------------- /train_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pgcool/textTOvec/HEAD/train_model.py -------------------------------------------------------------------------------- /train_model_lstm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pgcool/textTOvec/HEAD/train_model_lstm.py --------------------------------------------------------------------------------