GitHub - akshayminocha5/apertium-non-standard-input-task: Futher improvement on this version can be seen at -> https://github.com/akshayminocha5/apertium-standardise ... The goal of building this module is to convert non-standard data to standard form, so that it can be used, in our case by Apertium for Machine Translation services.

akshayminocha5 / apertium-non-standard-input-task Public

Notifications You must be signed in to change notification settings
Fork 0
Star 0

Futher improvement on this version can be seen at -> https://github.com/akshayminocha5/apertium-standardise ... The goal of building this module is to convert non-standard data to standard form, so that it can be used, in our case by Apertium for Machine Translation services.

0 stars 0 forks Branches Tags Activity

Star

Notifications

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 4 Commits
Flowchart_ksnmi_Non_standard.png		Flowchart_ksnmi_Non_standard.png
README		README
abbr_dict_en		abbr_dict_en
abbreviations_replace.py		abbreviations_replace.py
apostrophe_correction.py		apostrophe_correction.py
apostrophe_en		apostrophe_en
apostrophe_error_en		apostrophe_error_en
apostrophe_list.txt		apostrophe_list.txt
bigrams_en		bigrams_en
capitals.py		capitals.py
easy_tokenize2.py		easy_tokenize2.py
emoticon_remove_regexp.py		emoticon_remove_regexp.py
emoticon_sample		emoticon_sample
emoticons_pickle		emoticons_pickle
emoticons_remove.py		emoticons_remove.py
escape_sequence_addition.py		escape_sequence_addition.py
extended_words_trim2.py		extended_words_trim2.py
hahe_en		hahe_en
hahe_es		hahe_es
language_identifier.py		language_identifier.py
original_candidate_format.py		original_candidate_format.py
repetitions_hahe.py		repetitions_hahe.py
run.sh		run.sh
sample2		sample2
sample3		sample3
selecting_best_candidate.py		selecting_best_candidate.py
superblank_addition.py		superblank_addition.py
t1		t1
temp_language		temp_language
trie_implementation.py		trie_implementation.py
trigrams_en		trigrams_en
unigram_count_en		unigram_count_en
wordlist_dic_all_words_en		wordlist_dic_all_words_en
wordlist_dic_en		wordlist_dic_en

Repository files navigation

Using the bash script run.sh ============

./run.sh <non_standard_file> <language>

if you do not specify the source language then the toolkit will automatically detect the language