├── README.md ├── baselines.ipynb ├── data ├── clustering │ ├── raw_toloka_answers │ │ ├── assignments_0525_full_cut.tsv │ │ ├── assignments_0527_full_cut.tsv │ │ └── assignments_0529_full_cut.tsv │ ├── ru_clustering_0525_urls.tsv │ ├── ru_clustering_0527_urls_final.tsv │ └── ru_clustering_0529_urls_final_v2.tsv ├── headline_generation │ └── headline_generation_answers.jsonl └── headline_selection │ ├── titles_markup_0525_urls.tsv │ ├── titles_markup_0527_urls.tsv │ └── titles_markup_0529_urls.tsv ├── toloka └── guidelines │ ├── headline_selection.html │ └── news_clustering.html └── train_mlm.py /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dialogue-evaluation/Russian-News-Clustering-and-Headline-Generation/HEAD/README.md -------------------------------------------------------------------------------- /baselines.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dialogue-evaluation/Russian-News-Clustering-and-Headline-Generation/HEAD/baselines.ipynb -------------------------------------------------------------------------------- /data/clustering/raw_toloka_answers/assignments_0525_full_cut.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dialogue-evaluation/Russian-News-Clustering-and-Headline-Generation/HEAD/data/clustering/raw_toloka_answers/assignments_0525_full_cut.tsv -------------------------------------------------------------------------------- /data/clustering/raw_toloka_answers/assignments_0527_full_cut.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dialogue-evaluation/Russian-News-Clustering-and-Headline-Generation/HEAD/data/clustering/raw_toloka_answers/assignments_0527_full_cut.tsv -------------------------------------------------------------------------------- /data/clustering/raw_toloka_answers/assignments_0529_full_cut.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dialogue-evaluation/Russian-News-Clustering-and-Headline-Generation/HEAD/data/clustering/raw_toloka_answers/assignments_0529_full_cut.tsv -------------------------------------------------------------------------------- /data/clustering/ru_clustering_0525_urls.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dialogue-evaluation/Russian-News-Clustering-and-Headline-Generation/HEAD/data/clustering/ru_clustering_0525_urls.tsv -------------------------------------------------------------------------------- /data/clustering/ru_clustering_0527_urls_final.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dialogue-evaluation/Russian-News-Clustering-and-Headline-Generation/HEAD/data/clustering/ru_clustering_0527_urls_final.tsv -------------------------------------------------------------------------------- /data/clustering/ru_clustering_0529_urls_final_v2.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dialogue-evaluation/Russian-News-Clustering-and-Headline-Generation/HEAD/data/clustering/ru_clustering_0529_urls_final_v2.tsv -------------------------------------------------------------------------------- /data/headline_generation/headline_generation_answers.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dialogue-evaluation/Russian-News-Clustering-and-Headline-Generation/HEAD/data/headline_generation/headline_generation_answers.jsonl -------------------------------------------------------------------------------- /data/headline_selection/titles_markup_0525_urls.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dialogue-evaluation/Russian-News-Clustering-and-Headline-Generation/HEAD/data/headline_selection/titles_markup_0525_urls.tsv -------------------------------------------------------------------------------- /data/headline_selection/titles_markup_0527_urls.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dialogue-evaluation/Russian-News-Clustering-and-Headline-Generation/HEAD/data/headline_selection/titles_markup_0527_urls.tsv -------------------------------------------------------------------------------- /data/headline_selection/titles_markup_0529_urls.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dialogue-evaluation/Russian-News-Clustering-and-Headline-Generation/HEAD/data/headline_selection/titles_markup_0529_urls.tsv -------------------------------------------------------------------------------- /toloka/guidelines/headline_selection.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dialogue-evaluation/Russian-News-Clustering-and-Headline-Generation/HEAD/toloka/guidelines/headline_selection.html -------------------------------------------------------------------------------- /toloka/guidelines/news_clustering.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dialogue-evaluation/Russian-News-Clustering-and-Headline-Generation/HEAD/toloka/guidelines/news_clustering.html -------------------------------------------------------------------------------- /train_mlm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dialogue-evaluation/Russian-News-Clustering-and-Headline-Generation/HEAD/train_mlm.py --------------------------------------------------------------------------------