├── .gitignore ├── README.md ├── create_dataset.py ├── data ├── dataset.details.txt ├── quora_duplicate_questions.tsv ├── test.dev.tsv ├── test.full.tsv ├── test.tiny.tsv ├── training.dev.tsv ├── training.full.tsv └── training.tiny.tsv ├── data_helpers.py ├── eval.py ├── eval.sh ├── models ├── __init__.py ├── baseline_nn.py ├── siamese_cnn.py ├── siamese_lstm.py └── siamese_lstm_cnn.py ├── report.pdf ├── shingling_baseline.py ├── tensorboard.sh ├── train.py └── train.sh /.gitignore: -------------------------------------------------------------------------------- 1 | *.pyc 2 | runs 3 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # quora-duplicate-question-cnn 2 | -------------------------------------------------------------------------------- /create_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tgaddair/quora-duplicate-question-detector/HEAD/create_dataset.py -------------------------------------------------------------------------------- /data/dataset.details.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tgaddair/quora-duplicate-question-detector/HEAD/data/dataset.details.txt -------------------------------------------------------------------------------- /data/quora_duplicate_questions.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tgaddair/quora-duplicate-question-detector/HEAD/data/quora_duplicate_questions.tsv -------------------------------------------------------------------------------- /data/test.dev.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tgaddair/quora-duplicate-question-detector/HEAD/data/test.dev.tsv -------------------------------------------------------------------------------- /data/test.full.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tgaddair/quora-duplicate-question-detector/HEAD/data/test.full.tsv -------------------------------------------------------------------------------- /data/test.tiny.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tgaddair/quora-duplicate-question-detector/HEAD/data/test.tiny.tsv -------------------------------------------------------------------------------- /data/training.dev.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tgaddair/quora-duplicate-question-detector/HEAD/data/training.dev.tsv -------------------------------------------------------------------------------- /data/training.full.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tgaddair/quora-duplicate-question-detector/HEAD/data/training.full.tsv -------------------------------------------------------------------------------- /data/training.tiny.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tgaddair/quora-duplicate-question-detector/HEAD/data/training.tiny.tsv -------------------------------------------------------------------------------- /data_helpers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tgaddair/quora-duplicate-question-detector/HEAD/data_helpers.py -------------------------------------------------------------------------------- /eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tgaddair/quora-duplicate-question-detector/HEAD/eval.py -------------------------------------------------------------------------------- /eval.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tgaddair/quora-duplicate-question-detector/HEAD/eval.sh -------------------------------------------------------------------------------- /models/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /models/baseline_nn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tgaddair/quora-duplicate-question-detector/HEAD/models/baseline_nn.py -------------------------------------------------------------------------------- /models/siamese_cnn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tgaddair/quora-duplicate-question-detector/HEAD/models/siamese_cnn.py -------------------------------------------------------------------------------- /models/siamese_lstm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tgaddair/quora-duplicate-question-detector/HEAD/models/siamese_lstm.py -------------------------------------------------------------------------------- /models/siamese_lstm_cnn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tgaddair/quora-duplicate-question-detector/HEAD/models/siamese_lstm_cnn.py -------------------------------------------------------------------------------- /report.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tgaddair/quora-duplicate-question-detector/HEAD/report.pdf -------------------------------------------------------------------------------- /shingling_baseline.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tgaddair/quora-duplicate-question-detector/HEAD/shingling_baseline.py -------------------------------------------------------------------------------- /tensorboard.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | tensorboard --logdir "./runs/${1}/summaries/" 4 | -------------------------------------------------------------------------------- /train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tgaddair/quora-duplicate-question-detector/HEAD/train.py -------------------------------------------------------------------------------- /train.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tgaddair/quora-duplicate-question-detector/HEAD/train.sh --------------------------------------------------------------------------------