Index

B

BaseSegmenter (class in hashformers.segmenter.segmenter) Beamsearch (class in hashformers.beamsearch.algorithm)

BertLM (class in hashformers.beamsearch.bert_lm) build_ensemble_df() (in module hashformers.experiments.utils) build_hashtag_container() (hashformers.segmenter.segmenter.TweetSegmenter method)

C

calculate_diff_scores() (in module hashformers.experiments.utils) calculateAccuracy() (hashformers.evaluation.modeler.Modeler method) calculateFScore() (hashformers.evaluation.modeler.Modeler method) calculatePrecision() (hashformers.evaluation.modeler.Modeler method) calculateRecall() (hashformers.evaluation.modeler.Modeler method)

calculateScore() (hashformers.evaluation.modeler.Modeler method) characters (hashformers.beamsearch.data_structures.Node attribute) coerce_segmenter_objects() (in module hashformers.segmenter.segmenter) compile_dict() (hashformers.segmenter.segmenter.TweetSegmenter method) countEntry() (hashformers.evaluation.modeler.Modeler method)

D

deleteEncodingLayers() (in module hashformers.segmenter.segmenter)

dictionary (hashformers.beamsearch.data_structures.ProbabilityDictionary attribute)

E

EkphrasisWordSegmenter (class in hashformers.segmenter.segmenter) enforce_prob_dict() (in module hashformers.beamsearch.data_structures) ensemble_rank (hashformers.segmenter.segmenter.WordSegmenterOutput attribute)

evaluate_df() (in module hashformers.experiments.evaluation) evaluate_dictionary() (in module hashformers.evaluation.utils) extract_hashtags() (hashformers.segmenter.segmenter.TweetSegmenter method)

F

filter_and_project_scores() (in module hashformers.experiments.utils) filter_top_k() (in module hashformers.experiments.evaluation)

find_segment() (hashformers.segmenter.segmenter.EkphrasisWordSegmenter method) flatten_list() (hashformers.beamsearch.algorithm.Beamsearch method)

G

get_probs() (hashformers.beamsearch.bert_lm.BertLM method) (hashformers.beamsearch.gpt2_lm.GPT2LM method) get_segmentations() (hashformers.beamsearch.data_structures.ProbabilityDictionary method)

get_top_k() (hashformers.beamsearch.data_structures.ProbabilityDictionary method) getRunCode() (hashformers.evaluation.modeler.Modeler method) GPT2LM (class in hashformers.beamsearch.gpt2_lm)

H

hashformers module hashformers.beamsearch module hashformers.beamsearch.algorithm module hashformers.beamsearch.bert_lm module hashformers.beamsearch.data_structures module hashformers.beamsearch.gpt2_lm module hashformers.beamsearch.model_lm module hashformers.beamsearch.reranker module hashformers.ensemble module hashformers.ensemble.top2_fusion module

hashformers.evaluation module hashformers.evaluation.modeler module hashformers.evaluation.utils module hashformers.experiments module hashformers.experiments.evaluation module hashformers.experiments.utils module hashformers.segmenter module hashformers.segmenter.segmenter module hashtag_set (hashformers.segmenter.segmenter.HashtagContainer attribute) HashtagContainer (class in hashformers.segmenter.segmenter) hashtags (hashformers.segmenter.segmenter.HashtagContainer attribute) hashtagSegmentor (hashformers.evaluation.modeler.Modeler attribute) hypothesis (hashformers.beamsearch.data_structures.Node attribute)

I

isFeatureOn() (hashformers.evaluation.modeler.Modeler method)

L

loadModelerParams() (hashformers.evaluation.modeler.Modeler method)

loadParameter() (hashformers.evaluation.modeler.Modeler method) loadParameters() (hashformers.evaluation.modeler.Modeler method)

M

Modeler (class in hashformers.evaluation.modeler) modelerParams (hashformers.evaluation.modeler.Modeler attribute) ModelLM (class in hashformers.beamsearch.model_lm) module hashformers hashformers.beamsearch hashformers.beamsearch.algorithm hashformers.beamsearch.bert_lm hashformers.beamsearch.data_structures hashformers.beamsearch.gpt2_lm hashformers.beamsearch.model_lm hashformers.beamsearch.reranker hashformers.ensemble hashformers.ensemble.top2_fusion hashformers.evaluation hashformers.evaluation.modeler hashformers.evaluation.utils hashformers.experiments hashformers.experiments.evaluation hashformers.experiments.utils hashformers.segmenter hashformers.segmenter.segmenter

N

n (hashformers.evaluation.modeler.Modeler attribute)

next_step() (hashformers.beamsearch.algorithm.Beamsearch method) Node (class in hashformers.beamsearch.data_structures)

O

output (hashformers.segmenter.segmenter.TweetSegmenterOutput attribute) (hashformers.segmenter.segmenter.WordSegmenterOutput attribute)

P

p (hashformers.evaluation.modeler.Modeler attribute) PaddedGPT2LMScorer (class in hashformers.beamsearch.gpt2_lm) predict() (hashformers.segmenter.segmenter.BaseSegmenter method)

ProbabilityDictionary (class in hashformers.beamsearch.data_structures) project_scores() (in module hashformers.experiments.utils) prune_segmenter_layers() (in module hashformers.segmenter.segmenter)

R

r (hashformers.evaluation.modeler.Modeler attribute) read_experiment_dataset() (in module hashformers.experiments.evaluation) RegexWordSegmenter (class in hashformers.segmenter.segmenter) replace_hashtags() (hashformers.segmenter.segmenter.TweetSegmenter method) replacement_dict (hashformers.segmenter.segmenter.HashtagContainer attribute) rerank() (hashformers.beamsearch.reranker.Reranker method)

Reranker (class in hashformers.beamsearch.reranker) reranker_rank (hashformers.segmenter.segmenter.WordSegmenterOutput attribute) reset() (hashformers.evaluation.modeler.Modeler method) reshape_tree() (hashformers.beamsearch.algorithm.Beamsearch method) run() (hashformers.beamsearch.algorithm.Beamsearch method) run_ensemble() (in module hashformers.ensemble.top2_fusion)

S

score (hashformers.beamsearch.data_structures.Node attribute) segment() (hashformers.segmenter.segmenter.EkphrasisWordSegmenter method) (hashformers.segmenter.segmenter.RegexWordSegmenter method) (hashformers.segmenter.segmenter.TweetSegmenter method) (hashformers.segmenter.segmenter.WordSegmenter method) segment_word() (hashformers.segmenter.segmenter.EkphrasisWordSegmenter method) (hashformers.segmenter.segmenter.RegexWordSegmenter method)

segmentation_generator() (hashformers.segmenter.segmenter.RegexWordSegmenter method) segmented_tweet_generator() (hashformers.segmenter.segmenter.TweetSegmenter method) segmenter_rank (hashformers.segmenter.segmenter.WordSegmenterOutput attribute) segmentFile() (hashformers.evaluation.modeler.Modeler method) segmentHashtag() (hashformers.evaluation.modeler.Modeler method)

T

t (hashformers.evaluation.modeler.Modeler attribute) test() (hashformers.evaluation.modeler.Modeler method) to_csv() (hashformers.beamsearch.data_structures.ProbabilityDictionary method) to_dataframe() (hashformers.beamsearch.data_structures.ProbabilityDictionary method) to_json() (hashformers.beamsearch.data_structures.ProbabilityDictionary method) top2_ensemble() (in module hashformers.ensemble.top2_fusion)

totalh (hashformers.evaluation.modeler.Modeler attribute) totals (hashformers.evaluation.modeler.Modeler attribute) train() (hashformers.evaluation.modeler.Modeler method) trim_tree() (hashformers.beamsearch.algorithm.Beamsearch method) TweetSegmenter (class in hashformers.segmenter.segmenter) TweetSegmenterOutput (class in hashformers.segmenter.segmenter) TwitterTextMatcher (class in hashformers.segmenter.segmenter)

U

update_probabilities() (hashformers.beamsearch.algorithm.Beamsearch method)

W

word_segmenter_output (hashformers.segmenter.segmenter.TweetSegmenterOutput attribute)

WordSegmenter (class in hashformers.segmenter.segmenter) WordSegmenterOutput (class in hashformers.segmenter.segmenter)