Benjamin Trent 408489310c [ML] add zero_shot_classification task for BERT nlp models (#77799) ... Zero-Shot classification allows for text classification tasks without a pre-trained collection of target labels. This is achieved through models trained on the Multi-Genre Natural Language Inference (MNLI) dataset. This dataset pairs text sequences with "entailment" clauses. An example could be: "Throughout all of history, man kind has shown itself resourceful, yet astoundingly short-sighted" could have been paired with the entailment clauses: ["This example is history", "This example is sociology"...]. This training set combined with the attention and semantic knowledge in modern day NLP models (BERT, BART, etc.) affords a powerful tool for ad-hoc text classification. See https://arxiv.org/abs/1909.00161 for a deeper explanation of the MNLI training and how zero-shot works. The zeroshot classification task is configured as follows: ```js { // <snip> model configuration </snip> "inference_config" : { "zero_shot_classification": { "classification_labels": ["entailment", "neutral", "contradiction"], // <1> "labels": ["sad", "glad", "mad", "rad"], // <2> "multi_label": false, // <3> "hypothesis_template": "This example is {}.", // <4> "tokenization": { /*<snip> tokenization configuration </snip>*/} } } } ``` * <1> For all zero_shot models, there returns 3 particular labels when classification the target sequence. "entailment" is the positive case, "neutral" the case where the sequence isn't positive or negative, and "contradiction" is the negative case * <2> This is an optional parameter for the default zero_shot labels to attempt to classify * <3> When returning the probabilities, should the results assume there is only one true label or multiple true labels * <4> The hypothesis template when tokenizing the labels. When combining with `sad` the sequence looks like `This example is sad.` For inference in a pipeline one may provide label updates: ```js { //<snip> pipeline definition </snip> "processors": [ //<snip> other processors </snip> { "inference": { // <snip> general configuration </snip> "inference_config": { "zero_shot_classification": { "labels": ["humanities", "science", "mathematics", "technology"], // <1> "multi_label": true // <2> } } } } //<snip> other processors </snip> ] } ``` * <1> The `labels` we care about, these replace the default ones if they exist. * <2> Should the results allow multiple true labels Similarly one may provide label changes against the `_infer` endpoint ```js { "docs":[{ "text_field": "This is a very happy person"}], "inference_config":{"zero_shot_classification":{"labels": ["glad", "sad", "bad", "rad"], "multi_label": false}} } ```		2021-09-28 09:38:23 -04:00
..
anomaly-detection	[ML] add new default char filter first_line_with_letters for machine learning categorization (#77457)	2021-09-09 10:09:57 -04:00
df-analytics/apis	[ML] add zero_shot_classification task for BERT nlp models (#77799)	2021-09-28 09:38:23 -04:00
images	[DOCS] Adds anomaly job health alert type docs (#76659)	2021-08-30 16:11:34 +02:00
ml-shared.asciidoc	[ML] add zero_shot_classification task for BERT nlp models (#77799)	2021-09-28 09:38:23 -04:00