recognizers-text-number

What it is and what it does

recognizers-text-number is a language-aware numeric entity recognizer extracted from Microsoft's broader Recognizers-Text project. It identifies and extracts numbers expressed in natural language—cardinals, ordinals, percentages, and ranges—from text and normalizes them to machine-readable form. The package wraps the base recognizers-text library and the regex dependency to provide language-specific parsing rules.

It is designed for NLP pipelines where numeric entities must be identified before downstream processing. The package supports full recognition in English, Chinese, French, Spanish, Portuguese, German, Italian, Turkish, Hindi, and Dutch, with partial support in Japanese, Korean, Arabic, and Swedish. It powers entity extraction in Microsoft's LUIS, Power Virtual Agents, and Bot Framework, and is available as a standalone package for integration into custom applications.

Use it for:

• Extract numeric values from user input in chatbots or conversational AI systems for order quantities or date ranges.
• Parse financial or scientific documents to identify amounts, percentages, and measurements in multiple languages.
• Normalize spoken or written numbers in multilingual customer support tickets for downstream analysis.
• Build NLP preprocessing pipelines that require numeric entity recognition before intent classification.
• Validate or standardize numeric input in forms or APIs that accept natural-language number expressions.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Recognizes and extracts numeric entities (cardinals, ordinals, percentages, ranges) from text in multiple languages, with support for English, Chinese, French, Spanish, Portuguese, German, Italian, Turkish, Hindi, and Dutch.

Yes, if you need multilingual numeric entity extraction and can accept that the package is in alpha status with no updates since 2019. The low install friction, active underlying repository, and MIT license make it a reasonable choice for NLP pipelines. However, verify that the specific language and entity types you need are supported, and be aware that the package itself is not actively maintained.

Install

recognizers-text-number on PyPI

pip install recognizers-text-number

uv add recognizers-text-number

poetry add recognizers-text-number

Installing recognizers-text-number

Before you install

Low friction: pure Python wheel with only two runtime dependencies (recognizers-text and regex). Maintenance status is active with recent commits, though the package itself has not been updated since 2019-11-12.

License in practice

MIT license permits commercial and private use with minimal restrictions; you must include a copy of the license and copyright notice in distributions.

Quickstart

pip install recognizers-text-number

from recognizers_text_number import recognize_number

result = recognize_number("I have twenty-three apples", "en-us")

Verify before relying

• Whether the package is actively maintained or if 2019-11-12 represents the final release despite the active repository status.
• Current Python version compatibility beyond the stated 3.6 support in classifiers.
• Whether partial language support (Japanese, Korean, Arabic, Swedish) is functional in this number-specific package.
• Specific numeric formats and edge cases supported (e.g., written percentages, range expressions).

Package facts

Evidence: recognizers_text_number-1.0.2a2-py3-none-any.whl

Keywords: nlp, nlp-entity-extraction, entity-extraction, parser-library

Tags

More Artificial Intelligence packages