Files

 master

/

notebooks

/

Copy path

Directory actions

More options

Directory actions

More options

Latest commit

 

History

History

/

notebooks

/

Top

Folders and files

Name		Name	Last commit message	Last commit date
parent directory ..
00_snorkel.ipynb		00_snorkel.ipynb
00_snorkel_names.ipynb		00_snorkel_names.ipynb
100_train_test_split.ipynb		100_train_test_split.ipynb
101_sample_query_names.ipynb		101_sample_query_names.ipynb
102_baseline.ipynb		102_baseline.ipynb
103_bucketize_nama.ipynb		103_bucketize_nama.ipynb
104_cluster.ipynb		104_cluster.ipynb
105_cluster_greedy.ipynb		105_cluster_greedy.ipynb
105_cluster_greedy_given.ipynb		105_cluster_greedy_given.ipynb
106_analyze_nicknames.ipynb		106_analyze_nicknames.ipynb
10_clean.ipynb		10_clean.ipynb
11_clean_preferred.ipynb		11_clean_preferred.ipynb
12_analyze_preferred.ipynb		12_analyze_preferred.ipynb
200_generate_triplets.ipynb		200_generate_triplets.ipynb
201_generate_phonemes.ipynb		201_generate_phonemes.ipynb
202_generate_ngrams.ipynb		202_generate_ngrams.ipynb
203_generate_bpe_tokenizer.ipynb		203_generate_bpe_tokenizer.ipynb
204_generate_subword_tokenizer.ipynb		204_generate_subword_tokenizer.ipynb
205_generate_common_non_negatives.ipynb		205_generate_common_non_negatives.ipynb
206_analyze_triplets.ipynb		206_analyze_triplets.ipynb
207_augment_triplets.ipynb		207_augment_triplets.ipynb
208_bi_encoder_margin_mse_loss.ipynb		208_bi_encoder_margin_mse_loss.ipynb
209_bi_encoder_mse_loss.ipynb		209_bi_encoder_mse_loss.ipynb
20_generate_pairs.ipynb		20_generate_pairs.ipynb
211_analyze_subclusters.ipynb		211_analyze_subclusters.ipynb
212_analyze_inter_cluster_similarity.ipynb		212_analyze_inter_cluster_similarity.ipynb
220_create_language_model_dataset.ipynb		220_create_language_model_dataset.ipynb
221_train_language_model.ipynb		221_train_language_model.ipynb
222_train_cross_encoder.ipynb		222_train_cross_encoder.ipynb
223_generate_triplets_from_cross_encoder.ipynb		223_generate_triplets_from_cross_encoder.ipynb
224_train_bi_encoder.ipynb		224_train_bi_encoder.ipynb
230_eval_bi_encoder.ipynb		230_eval_bi_encoder.ipynb
240_create_clusters_from_buckets.ipynb		240_create_clusters_from_buckets.ipynb
241_augment_clusters.ipynb		241_augment_clusters.ipynb
242_nearby_clusters.ipynb		242_nearby_clusters.ipynb
243_compress_cluster_files.ipynb		243_compress_cluster_files.ipynb
245_eval_coder.ipynb		245_eval_coder.ipynb
246_generate_clusters_from_bi_encoder.ipynb		246_generate_clusters_from_bi_encoder.ipynb
250_create_phonebook.ipynb		250_create_phonebook.ipynb
251_save_bi_encoder_weights.ipynb		251_save_bi_encoder_weights.ipynb
30_aggregate.ipynb		30_aggregate.ipynb
310_clean.ipynb		310_clean.ipynb
311_clean_preferred.ipynb		311_clean_preferred.ipynb
31_aggregate_preferred.ipynb		31_aggregate_preferred.ipynb
31b_aggregate_hr.ipynb		31b_aggregate_hr.ipynb
320_generate_pairs.ipynb		320_generate_pairs.ipynb
32_analyze_aggregate_preferred.ipynb		32_analyze_aggregate_preferred.ipynb
330_aggregate.ipynb		330_aggregate.ipynb
331_aggregate_preferred.ipynb		331_aggregate_preferred.ipynb
340_filter.ipynb		340_filter.ipynb
345_train_test_split.ipynb		345_train_test_split.ipynb
360_augment_train_for_swivel.ipynb		360_augment_train_for_swivel.ipynb
361_tune_swivel.ipynb		361_tune_swivel.ipynb
362_train_swivel.ipynb		362_train_swivel.ipynb
363_analyze_swivel.ipynb		363_analyze_swivel.ipynb
364_generate_triplets_from_swivel.ipynb		364_generate_triplets_from_swivel.ipynb
370_generate_triplets_for_cross_encoder.ipynb		370_generate_triplets_for_cross_encoder.ipynb
371_generate_common_non_negatives.ipynb		371_generate_common_non_negatives.ipynb
372_generate_subword_tokenizer.ipynb		372_generate_subword_tokenizer.ipynb
373_augment_triplets_for_cross_encoder.ipynb		373_augment_triplets_for_cross_encoder.ipynb
375_train_language_model.ipynb		375_train_language_model.ipynb
377_train_cross_encoder.ipynb		377_train_cross_encoder.ipynb
378_generate_triplets_from_cross_encoder.ipynb		378_generate_triplets_from_cross_encoder.ipynb
380_train_bi_encoder.ipynb		380_train_bi_encoder.ipynb
381_eval_bi_encoder.ipynb		381_eval_bi_encoder.ipynb
390_create_clusters_from_buckets.ipynb		390_create_clusters_from_buckets.ipynb
391_augment_clusters.ipynb		391_augment_clusters.ipynb
393_compress_cluster_files.ipynb		393_compress_cluster_files.ipynb
394_eval_coder.ipynb		394_eval_coder.ipynb
395_create_phonebook.ipynb		395_create_phonebook.ipynb
396_save_bi_encoder_weights.ipynb		396_save_bi_encoder_weights.ipynb
40_filter.ipynb		40_filter.ipynb
41_generate_nicknames.ipynb		41_generate_nicknames.ipynb
46_demo_dataset.ipynb		46_demo_dataset.ipynb
47_bad_pair_generator.ipynb		47_bad_pair_generator.ipynb
47a_filter_bad_pairs.ipynb		47a_filter_bad_pairs.ipynb
48_weighted_actual_names_to_csv.ipynb		48_weighted_actual_names_to_csv.ipynb
49_augment_dataset.ipynb		49_augment_dataset.ipynb
50_autoencoder.ipynb		50_autoencoder.ipynb
51_autoencoder_triplet.ipynb		51_autoencoder_triplet.ipynb
52_glove.ipynb		52_glove.ipynb
60_swivel_tune.ipynb		60_swivel_tune.ipynb
61_swivel.ipynb		61_swivel.ipynb
62_swivel_encoder_tune.ipynb		62_swivel_encoder_tune.ipynb
63_swivel_encoder.ipynb		63_swivel_encoder.ipynb
64_analyze_scores.ipynb		64_analyze_scores.ipynb
65_tfidf.ipynb		65_tfidf.ipynb
66_ensemble.ipynb		66_ensemble.ipynb
70_compare_similarity.ipynb		70_compare_similarity.ipynb
71_analyze_embeddings.ipynb		71_analyze_embeddings.ipynb
72_analyze_names.ipynb		72_analyze_names.ipynb
80_cluster_tune.ipynb		80_cluster_tune.ipynb
81_cluster.ipynb		81_cluster.ipynb
82_cluster_levenshtein.ipynb		82_cluster_levenshtein.ipynb
90_compare_coders.ipynb		90_compare_coders.ipynb
91_compare_old_algo.ipynb		91_compare_old_algo.ipynb
92_compare_oov_approaches.ipynb		92_compare_oov_approaches.ipynb
93_compare_swivel_vectors_to_co-occurrences.ipynb		93_compare_swivel_vectors_to_co-occurrences.ipynb
97_analyze_nicknames.ipynb		97_analyze_nicknames.ipynb
98_given_surname_freq.ipynb		98_given_surname_freq.ipynb
99_precompute.ipynb		99_precompute.ipynb
View all files