├── README.md ├── analysis.ipynb ├── data ├── .DS_Store ├── 20ng │ ├── 1_convert_prodlda_to_txt_py27.py │ ├── 2_convert_txt_to_scholar_format_py3.py │ ├── 3_replicate_and_align_raw_data.py │ ├── 4_create_dev_sets.py │ ├── 5_create_aligned_dev_set.py │ ├── 6_create_raw_text_file.py │ ├── Readme.md │ └── utils.py ├── imdb │ ├── create_dev_split.py │ ├── download_imdb.py │ ├── file_handling.py │ ├── preprocess_data.py │ └── utils.py └── wiki │ ├── original-parsing.sh │ ├── utils.py │ └── wikitext103_wae.py ├── scholar ├── .gitignore ├── LICENSE ├── compute_npmi.py ├── download_imdb.py ├── file_handling.py ├── multiple_run_scholar.py ├── preprocess_data.py ├── run_scholar.py ├── scholar.bib ├── scholar.py ├── scholar.yml ├── split_data.py └── stopwords │ ├── custom_stopwords.txt │ ├── mallet_stopwords.txt │ └── snowball_stopwords.txt ├── teacher ├── bert_reconstruction.py ├── run_language_modeling.py └── teacher.yml └── w-lda ├── .gitignore ├── CODE_OF_CONDUCT.md ├── CONTRIBUTING.md ├── LICENSE ├── NOTICE ├── README.md ├── compute_op.py ├── core.py ├── examples ├── args │ ├── 20news_sklearn_wae │ │ └── mmd.txt │ ├── ag_news_csv │ │ └── mmd.txt │ ├── dbpedia_csv │ │ └── mmd.txt │ ├── lda_synthetic │ │ └── mmd.txt │ ├── nytimes-pbr │ │ └── mmd.txt │ ├── wikitext-103 │ │ └── mmd.txt │ └── yelp_review_polarity_csv │ │ └── mmd.txt ├── domains │ ├── ag_news_wae.py │ ├── dbpedia_wae.py │ ├── lda_synthetic.py │ ├── nyt_wae.py │ ├── processed_data_wae.py │ ├── twenty_news_sklearn_wae.py │ ├── wikitext103_wae.py │ └── yelp_polarity_wae.py └── gpu0.sh ├── models └── dirichlet.py ├── npmi_calc.py ├── run.py ├── utils.py └── w-lda.yml /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/README.md -------------------------------------------------------------------------------- /analysis.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/analysis.ipynb -------------------------------------------------------------------------------- /data/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/data/.DS_Store -------------------------------------------------------------------------------- /data/20ng/1_convert_prodlda_to_txt_py27.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/data/20ng/1_convert_prodlda_to_txt_py27.py -------------------------------------------------------------------------------- /data/20ng/2_convert_txt_to_scholar_format_py3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/data/20ng/2_convert_txt_to_scholar_format_py3.py -------------------------------------------------------------------------------- /data/20ng/3_replicate_and_align_raw_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/data/20ng/3_replicate_and_align_raw_data.py -------------------------------------------------------------------------------- /data/20ng/4_create_dev_sets.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/data/20ng/4_create_dev_sets.py -------------------------------------------------------------------------------- /data/20ng/5_create_aligned_dev_set.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/data/20ng/5_create_aligned_dev_set.py -------------------------------------------------------------------------------- /data/20ng/6_create_raw_text_file.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/data/20ng/6_create_raw_text_file.py -------------------------------------------------------------------------------- /data/20ng/Readme.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/data/20ng/Readme.md -------------------------------------------------------------------------------- /data/20ng/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/data/20ng/utils.py -------------------------------------------------------------------------------- /data/imdb/create_dev_split.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/data/imdb/create_dev_split.py -------------------------------------------------------------------------------- /data/imdb/download_imdb.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/data/imdb/download_imdb.py -------------------------------------------------------------------------------- /data/imdb/file_handling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/data/imdb/file_handling.py -------------------------------------------------------------------------------- /data/imdb/preprocess_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/data/imdb/preprocess_data.py -------------------------------------------------------------------------------- /data/imdb/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/data/imdb/utils.py -------------------------------------------------------------------------------- /data/wiki/original-parsing.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/data/wiki/original-parsing.sh -------------------------------------------------------------------------------- /data/wiki/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/data/wiki/utils.py -------------------------------------------------------------------------------- /data/wiki/wikitext103_wae.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/data/wiki/wikitext103_wae.py -------------------------------------------------------------------------------- /scholar/.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/scholar/.gitignore -------------------------------------------------------------------------------- /scholar/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/scholar/LICENSE -------------------------------------------------------------------------------- /scholar/compute_npmi.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/scholar/compute_npmi.py -------------------------------------------------------------------------------- /scholar/download_imdb.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/scholar/download_imdb.py -------------------------------------------------------------------------------- /scholar/file_handling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/scholar/file_handling.py -------------------------------------------------------------------------------- /scholar/multiple_run_scholar.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/scholar/multiple_run_scholar.py -------------------------------------------------------------------------------- /scholar/preprocess_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/scholar/preprocess_data.py -------------------------------------------------------------------------------- /scholar/run_scholar.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/scholar/run_scholar.py -------------------------------------------------------------------------------- /scholar/scholar.bib: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/scholar/scholar.bib -------------------------------------------------------------------------------- /scholar/scholar.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/scholar/scholar.py -------------------------------------------------------------------------------- /scholar/scholar.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/scholar/scholar.yml -------------------------------------------------------------------------------- /scholar/split_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/scholar/split_data.py -------------------------------------------------------------------------------- /scholar/stopwords/custom_stopwords.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/scholar/stopwords/custom_stopwords.txt -------------------------------------------------------------------------------- /scholar/stopwords/mallet_stopwords.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/scholar/stopwords/mallet_stopwords.txt -------------------------------------------------------------------------------- /scholar/stopwords/snowball_stopwords.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/scholar/stopwords/snowball_stopwords.txt -------------------------------------------------------------------------------- /teacher/bert_reconstruction.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/teacher/bert_reconstruction.py -------------------------------------------------------------------------------- /teacher/run_language_modeling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/teacher/run_language_modeling.py -------------------------------------------------------------------------------- /teacher/teacher.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/teacher/teacher.yml -------------------------------------------------------------------------------- /w-lda/.gitignore: -------------------------------------------------------------------------------- 1 | __pycache__ 2 | *.pyc 3 | examples/results -------------------------------------------------------------------------------- /w-lda/CODE_OF_CONDUCT.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/w-lda/CODE_OF_CONDUCT.md -------------------------------------------------------------------------------- /w-lda/CONTRIBUTING.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/w-lda/CONTRIBUTING.md -------------------------------------------------------------------------------- /w-lda/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/w-lda/LICENSE -------------------------------------------------------------------------------- /w-lda/NOTICE: -------------------------------------------------------------------------------- 1 | Copyright 2019 Amazon.com, Inc. or its affiliates. All Rights Reserved. 2 | -------------------------------------------------------------------------------- /w-lda/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/w-lda/README.md -------------------------------------------------------------------------------- /w-lda/compute_op.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/w-lda/compute_op.py -------------------------------------------------------------------------------- /w-lda/core.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/w-lda/core.py -------------------------------------------------------------------------------- /w-lda/examples/args/20news_sklearn_wae/mmd.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/w-lda/examples/args/20news_sklearn_wae/mmd.txt -------------------------------------------------------------------------------- /w-lda/examples/args/ag_news_csv/mmd.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/w-lda/examples/args/ag_news_csv/mmd.txt -------------------------------------------------------------------------------- /w-lda/examples/args/dbpedia_csv/mmd.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/w-lda/examples/args/dbpedia_csv/mmd.txt -------------------------------------------------------------------------------- /w-lda/examples/args/lda_synthetic/mmd.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/w-lda/examples/args/lda_synthetic/mmd.txt -------------------------------------------------------------------------------- /w-lda/examples/args/nytimes-pbr/mmd.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/w-lda/examples/args/nytimes-pbr/mmd.txt -------------------------------------------------------------------------------- /w-lda/examples/args/wikitext-103/mmd.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/w-lda/examples/args/wikitext-103/mmd.txt -------------------------------------------------------------------------------- /w-lda/examples/args/yelp_review_polarity_csv/mmd.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/w-lda/examples/args/yelp_review_polarity_csv/mmd.txt -------------------------------------------------------------------------------- /w-lda/examples/domains/ag_news_wae.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/w-lda/examples/domains/ag_news_wae.py -------------------------------------------------------------------------------- /w-lda/examples/domains/dbpedia_wae.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/w-lda/examples/domains/dbpedia_wae.py -------------------------------------------------------------------------------- /w-lda/examples/domains/lda_synthetic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/w-lda/examples/domains/lda_synthetic.py -------------------------------------------------------------------------------- /w-lda/examples/domains/nyt_wae.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/w-lda/examples/domains/nyt_wae.py -------------------------------------------------------------------------------- /w-lda/examples/domains/processed_data_wae.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/w-lda/examples/domains/processed_data_wae.py -------------------------------------------------------------------------------- /w-lda/examples/domains/twenty_news_sklearn_wae.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/w-lda/examples/domains/twenty_news_sklearn_wae.py -------------------------------------------------------------------------------- /w-lda/examples/domains/wikitext103_wae.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/w-lda/examples/domains/wikitext103_wae.py -------------------------------------------------------------------------------- /w-lda/examples/domains/yelp_polarity_wae.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/w-lda/examples/domains/yelp_polarity_wae.py -------------------------------------------------------------------------------- /w-lda/examples/gpu0.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/w-lda/examples/gpu0.sh -------------------------------------------------------------------------------- /w-lda/models/dirichlet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/w-lda/models/dirichlet.py -------------------------------------------------------------------------------- /w-lda/npmi_calc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/w-lda/npmi_calc.py -------------------------------------------------------------------------------- /w-lda/run.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/w-lda/run.py -------------------------------------------------------------------------------- /w-lda/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/w-lda/utils.py -------------------------------------------------------------------------------- /w-lda/w-lda.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ahoho/kd-topic-models/HEAD/w-lda/w-lda.yml --------------------------------------------------------------------------------