|
19 | 19 | </h2> |
20 | 20 |
|
21 | 21 | <palign="center"> |
22 | | -Simple machine learning with |
| 22 | +Generative AI with |
23 | 23 | <a href="https://www.postgresql.org/" target="_blank">PostgreSQL</a> |
24 | 24 | </p> |
25 | 25 |
|
@@ -408,9 +408,61 @@ SELECT pgml.transform( |
408 | 408 | ] |
409 | 409 | ``` |
410 | 410 | ##Token Classification |
411 | | -##Table Question Answering |
412 | | -##Question Answering |
| 411 | +Token classification is a task in natural language understanding, where labels are assigned to certain tokens in a text. Some popular subtasks of token classification include Named Entity Recognition (NER) and Part-of-Speech (PoS) tagging. NER models can be trained to identify specific entities in a text, such as individuals, places, and dates. PoS tagging, on the other hand, is used to identify the different parts of speech in a text, such as nouns, verbs, and punctuation marks. |
| 412 | + |
| 413 | + |
413 | 414 |
|
| 415 | +###Named Entity Recognition |
| 416 | +Named Entity Recognition (NER) is a task that involves identifying named entities in a text. These entities can include the names of people, locations, or organizations. The task is completed by labeling each token with a class for each named entity and a class named "0" for tokens that don't contain any entities. In this task, the input is text, and the output is the annotated text with named entities. |
| 417 | + |
| 418 | +```sql |
| 419 | +SELECTpgml.transform( |
| 420 | + inputs=> ARRAY[ |
| 421 | +'I am Omar and I live in New York City.' |
| 422 | + ], |
| 423 | + task=>'token-classification' |
| 424 | +)as ner; |
| 425 | +``` |
| 426 | +*Result* |
| 427 | +```sql |
| 428 | + ner |
| 429 | +------------------------------------------------------ |
| 430 | +[[ |
| 431 | + {"end":9,"word":"Omar","index":3,"score":0.997110,"start":5,"entity":"I-PER"}, |
| 432 | + {"end":27,"word":"New","index":8,"score":0.999372,"start":24,"entity":"I-LOC"}, |
| 433 | + {"end":32,"word":"York","index":9,"score":0.999355,"start":28,"entity":"I-LOC"}, |
| 434 | + {"end":37,"word":"City","index":10,"score":0.999431,"start":33,"entity":"I-LOC"} |
| 435 | +]] |
| 436 | +``` |
| 437 | + |
| 438 | +###Part-of-Speech (PoS) Tagging |
| 439 | +PoS tagging is a task that involves identifying the parts of speech, such as nouns, pronouns, adjectives, or verbs, in a given text. In this task, the model labels each word with a specific part of speech. |
| 440 | + |
| 441 | +Look for models with`pos` to use a zero-shot classification model on the:hugs: Hugging Face model hub. |
| 442 | +```sql |
| 443 | +selectpgml.transform( |
| 444 | +inputs=> array [ |
| 445 | +'I live in Amsterdam.' |
| 446 | +], |
| 447 | +task=>'{"task": "token-classification", |
| 448 | + "model": "vblagoje/bert-english-uncased-finetuned-pos" |
| 449 | + }'::JSONB |
| 450 | +)as pos; |
| 451 | +``` |
| 452 | +*Result* |
| 453 | +```sql |
| 454 | + pos |
| 455 | +------------------------------------------------------ |
| 456 | +[[ |
| 457 | + {"end":1,"word":"i","index":1,"score":0.999,"start":0,"entity":"PRON"}, |
| 458 | + {"end":6,"word":"live","index":2,"score":0.998,"start":2,"entity":"VERB"}, |
| 459 | + {"end":9,"word":"in","index":3,"score":0.999,"start":7,"entity":"ADP"}, |
| 460 | + {"end":19,"word":"amsterdam","index":4,"score":0.998,"start":10,"entity":"PROPN"}, |
| 461 | + {"end":20,"word":".","index":5,"score":0.999,"start":19,"entity":"PUNCT"} |
| 462 | +]] |
| 463 | +``` |
| 464 | +##Question Answering |
| 465 | +##Table Question Answering |
414 | 466 | ##Translation |
415 | 467 | ##Summarization |
416 | 468 | ##Conversational |
|