explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-07-13 09:42:26 +03:00
Code Issues Packages Projects Releases Wiki Activity

Merge 2d1891c69f into 41e07772dc

Browse Source
This commit is contained in:
Ilie 2025-06-22 00:32:41 +03:00 committed by GitHub
commit 71dda9dcc5
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 17 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
website/meta/universe.json
View File

@ -3,7 +3,7 @@
{ {
"id": "TeNs", "id": "TeNs",
"title": "Temporal Expressions Normalization spaCy", "title": "Temporal Expressions Normalization spaCy",
"thumb": "https://github-production-user-asset-6210df.s3.amazonaws.com/40547052/433595900-fae3c9d9-7181-4d8b-8b49-e6dc4fca930b.png?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=AKIAVCODYLSA53PQK4ZA%2F20250414%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20250414T235545Z&X-Amz-Expires=300&X-Amz-Signature=e21d3c06300ceb15fa1dadd7cb60081cc9f1b35e5a7bfd07f6e8b90dd7fad9d0&X-Amz-SignedHeaders=host", "thumb": "https://raw.githubusercontent.com/iliedorobat/timespan-normalization-spacy/refs/heads/main/icon.png",
"url": "https://pypi.org/project/temporal-normalization-spacy/", "url": "https://pypi.org/project/temporal-normalization-spacy/",
"slogan": "A temporal expression normalization plugin for Romanian using rule-based methods and DBpedia mappings.", "slogan": "A temporal expression normalization plugin for Romanian using rule-based methods and DBpedia mappings.",
"description": "**[Temporal Expressions Normalization spaCy (TeNs)](https://github.com/iliedorobat/timespan-normalization-spacy)** is a powerful pipeline component for spaCy that seamlessly identifies and parses date entities in text. It leverages the **[Temporal Expressions Normalization Framework]( https://github.com/iliedorobat/timespan-normalization)** to recognize a wide variety of date formats using an extensive set of regular expressions (RegEx), ensuring robust and adaptable date extraction across diverse textual sources.\n\nUnlike conventional solutions that primarily focus on well-structured date formats, TeNs excels in handling real-world text by **identifying** not only standard date representations but also **abbreviated, informal, or even misspelled temporal expressions.** This makes it particularly effective for processing noisy or unstructured data, such as historical records, user-generated content, and scanned documents with OCR inaccuracies.", "description": "**[Temporal Expressions Normalization spaCy (TeNs)](https://github.com/iliedorobat/timespan-normalization-spacy)** is a powerful pipeline component for spaCy that seamlessly identifies and parses date entities in text. It leverages the **[Temporal Expressions Normalization Framework]( https://github.com/iliedorobat/timespan-normalization)** to recognize a wide variety of date formats using an extensive set of regular expressions (RegEx), ensuring robust and adaptable date extraction across diverse textual sources.\n\nUnlike conventional solutions that primarily focus on well-structured date formats, TeNs excels in handling real-world text by **identifying** not only standard date representations but also **abbreviated, informal, or even misspelled temporal expressions.** This makes it particularly effective for processing noisy or unstructured data, such as historical records, user-generated content, and scanned documents with OCR inaccuracies.",
@ -34,21 +34,25 @@
"", "",
"# Display information about the identified and normalized dates in the text.", "# Display information about the identified and normalized dates in the text.",
"for entity in doc.ents:", "for entity in doc.ents:",
" edges = entity._.time_series.edges", " time_series = entity._.time_series",
"", "",
" print('Start Edge:')", " if isinstance(time_series, list):",
" print(edges.start.serialize('\\t'))", " for ts in time_series:",
" print()", " edges = ts.edges",
"", "",
" print('End Edge:')", " print('Start Edge:')",
" print(edges.end.serialize('\\t'))", " print(edges.start.serialize('\\t'))",
" print()", " print()",
"", "",
" print('Periods:')", " print('End Edge:')",
" for period in entity._.time_series.periods:", " print(edges.end.serialize('\\t'))",
" print(period.serialize('\\t'))", " print()",
" print()", "",
" print('---------------------')" " print('Periods:')",
" for period in ts.periods:",
" print(period.serialize('\\t'))",
" print()",
" print('---------------------')"
], ],
"code_language": "python", "code_language": "python",
"author": "Ilie Cristian Dorobat", "author": "Ilie Cristian Dorobat",