explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-11-04 01:48:04 +03:00
Code Issues Packages Projects Releases Wiki Activity

chore: added adept-augmentations to the spacy universe (#12609)

Browse Source 
* chore: added adept-augmentations to the spacy universe

* Apply suggestions from code review

Co-authored-by: Basile Dura <bdura@users.noreply.github.com>

* Update universe.json

---------

Co-authored-by: Basile Dura <bdura@users.noreply.github.com>
This commit is contained in:
David Berenstein 2023-05-10 13:16:16 +02:00 committed by Adriane Boyd
parent 54d9198e62
commit 81488fa88b
1 changed files with 50 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

50
website/meta/universe.json
View File

@ -2837,6 +2837,56 @@
"tags": ["coreference", "multi-lingual", "cross-lingual", "allennlp"], "tags": ["coreference", "multi-lingual", "cross-lingual", "allennlp"],
"spacy_version": 3 "spacy_version": 3
}, },
{
"id": "adeptaugmentations",
"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",
"pip": "adept-augmentations",
"thumb": "https://raw.githubusercontent.com/Pandora-Intelligence/crosslingual-coreference/master/img/logo.png",
"code_example": [
"import spacy",
"from spacy.tokens import DocBin",
"",
"from adept_augmentations import EntitySwapAugmenter",
"",
"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\"",
"]",
"docs = nlp.pipe(TRAIN_DATA)",
"",
"# Create a new DocBin",
"doc_bin = DocBin(docs=docs)",
"",
"# Augment Data",
"doc_bin = EntitySwapAugmenter(doc_bin).augment(4)",
"for doc in doc_bin.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",
"# GitHub is looking at buying U.K. startup for $ 1 billion",
"# Microsoft acquires Apple for $ 7.5 billion",
"# Apple acquires Microsoft for $ 1 billion",
"# Microsoft acquires Microsoft for $ 7.5 billion",
"# GitHub acquires GitHub for $ 1 billion"
],
"author": "David Berenstein",
"author_links": {
"github": "davidberenstein1957",
"website": "https://www.linkedin.com/in/david-berenstein-1bab11105/"
},
"category": ["standalone"],
"tags": ["ner", "few-shot", "augmentation", "datasets", "training"],
"spacy_version": 3
},
{ {
"id": "blackstone", "id": "blackstone",
"title": "Blackstone", "title": "Blackstone",