...
| Code Block |
|---|
{
"add_lemmization": false, # add lemmization to the words
"cache_lemmas": false, # save the lemmas in a cache to improve the peroformances
"filter_list": [], # List of terms you do not want to see
"input_field": [ "body"], # where get the input text
"max_chunk_len": 2, # min number of words in a chunk
"min_word_len": 4, # min character in a words
"output_field": "terms", #where store the output (list)
"p_significant_terms": 0.2, # % of timportantimportant terms to pickup
"save_model": true, #save the generate model
"step": "embedder",
"type": "terms_extraction"
}, |
...