explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-24 17:06:29 +03:00
Code Issues Packages Projects Releases Wiki Activity

universe: Update examples Adept Augementation (#12620)

Browse Source 
* Update universe.json

* chore: changed readme example as suggested by Vincent Warmerdam (koaning)
This commit is contained in:
David Berenstein 2023-05-15 14:09:33 +02:00 committed by GitHub
parent 3dc445df8d
commit 83b6f488cb
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 18 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
website/meta/universe.json
View File

@ -2865,33 +2865,35 @@
"title": "Adept Augmentations",
"slogan": " A Python library aimed at dissecting and augmenting NER training data for a few-shot scenario.",
"description": "EntitySwapAugmenter takes either a `datasets.Dataset` or a `spacy.tokens.DocBin`. Additionally, it is optional to provide a set of labels. It initially creates a knowledge base of entities belonging to a certain label. When running `augmenter.augment()` for N runs, it then creates N new sentences with random swaps of the original entities with an entity of the same corresponding label from the knowledge base.\n\nFor example, assuming that we have knowledge base for `PERSONS`, `LOCATIONS` and `PRODUCTS`. We can then create additional data for the sentence \"Momofuko Ando created instant noodles in Osaka.\" using `augmenter.augment(N=2)`, resulting in \"David created instant noodles in Madrid.\" or \"Tom created Adept Augmentations in the Netherlands\".",
"github": "davidberenstein1957/adept-augmentations",
"github": "argilla-io/adept-augmentations",
"pip": "adept-augmentations",
"thumb": "https://raw.githubusercontent.com/Pandora-Intelligence/crosslingual-coreference/master/img/logo.png",
"thumb": "https://raw.githubusercontent.com/argilla-io/adept-augmentations/main/logo.png",
"code_example": [
"import spacy",
"from spacy.tokens import DocBin",
"",
"from adept_augmentations import EntitySwapAugmenter",
"import spacy",
"from spacy.tokens import Doc, DocBin",
"nlp = spacy.blank(\"en\")",
"",
"nlp = spacy.load(\"en_core_web_sm\")",
"",
"TRAIN_DATA = [",
" \"Apple is looking at buying U.K. startup for $1 billion\",",
" \"Microsoft acquires GitHub for $7.5 billion\"",
"# Create some example golden data",
"example_data = [",
" (\"Apple is looking at buying U.K. startup for $1 billion\", [(0, 5, \"ORG\"), (27, 31, \"LOC\"), (44, 54, \"MONEY\")]),",
" (\"Microsoft acquires GitHub for $7.5 billion\", [(0, 9, \"ORG\"), (19, 25, \"ORG\"), (30, 42, \"MONEY\")]),",
"]",
"docs = nlp.pipe(TRAIN_DATA)",
"",
"# Create a new DocBin",
"doc_bin = DocBin(docs=docs)",
"nlp = spacy.blank(\"en\")",
"docs = []",
"for entry in example_data:",
" doc = Doc(nlp.vocab, words=entry[0].split())",
" doc.ents = [doc.char_span(ent[0], ent[1], label=ent[2]) for ent in entry[1]]",
" docs.append(doc)",
"golden_dataset = DocBin(docs=docs)",
"",
"# Augment Data",
"doc_bin = EntitySwapAugmenter(doc_bin).augment(4)",
"for doc in doc_bin.get_docs(nlp.vocab):",
"augmented_dataset = EntitySwapAugmenter(golden_dataset).augment(4)",
"for doc in augmented_dataset.get_docs(nlp.vocab):",
" print(doc.text)",
"",
"# Output",
"#",
"# GitHub is looking at buying U.K. startup for $ 7.5 billion",
"# Microsoft is looking at buying U.K. startup for $ 1 billion",
"# Microsoft is looking at buying U.K. startup for $ 7.5 billion",