Packages
Extracts entities, relations, and linguistic structures from text and documents using pretrained NLP models, then constructs knowledge graphs from the extracted information.
Install only if the core NLP and graph-building features match your needs and you can tolerate potential staleness.
GiNZA is a Japanese NLP library that performs tokenization, part-of-speech tagging, dependency parsing, and named entity recognition on Japanese text using Universal Dependencies standards.
Install it if you're working with Japanese text and need structured linguistic analysis; the main trade-off is that transformer models require downloading large files…
Polyglot is a multilingual natural language processing pipeline that performs tokenization, language detection, named entity recognition, part-of-speech tagging, sentiment analysis, word embeddings, morphological analysis, and transliteration across many languages.
No—not for new projects.
Extends Python's built-in unicodedata module with additional Unicode properties like script, block, emoji attributes, and break properties for characters.
Normalizes Bangla Unicode text by fixing invalid character sequences, handling legacy symbols, and optionally preserving English text.
Detects the language of text using Google's Compact Language Detector v3, returning language codes and confidence scores for over 100 languages and scripts.
No, not recommended for new projects.
Adds a spaCy pipeline component that identifies date entities in text using regex and converts them to structured datetime objects via dateparser, storing results in a custom token extension.
However, it is abandoned (last updated 2023-08-24) with no ongoing maintenance, so install only if the fixed functionality is sufficient and you do not expect bug…
Implements the Soundex phonetic algorithm for indexing names by sound in English, plus a modified version for Indian languages.
Penman is a Python library for reading, writing, and manipulating graphs encoded in PENMAN notation, commonly used for Abstract Meaning Representation (AMR) and other semantic graph formats.
Provides common utility functions for SILPA, including character mapping for Indic languages and language detection capabilities.
Python bindings to libpostal, a C library for parsing and normalizing street addresses worldwide, supporting address expansion and component extraction.
A pre-trained Japanese NLP model for spaCy that performs tokenization, dependency parsing, named entity recognition, part-of-speech tagging, and morphological analysis on Japanese text.
Computes ROUGE evaluation metrics for Chinese text summarization and NLP tasks, handling Chinese punctuation and sentence segmentation correctly.
However, verify that the unclear license aligns with your use case, and confirm compatibility with your Python version since support is unspecified.
Sastrawi reduces inflected Indonesian words to their base form (stem) by removing prefixes, suffixes, and other morphological variations.
Command-line tool for extracting, compiling, validating, and managing translations in Django projects and apps, with integration for uploading to and downloading from Transifex.
Madoka implements a Count-Min sketch data structure for memory-efficient counting of string-int pairs in streaming data, with lower memory overhead than Python dict or Counter.
Provides a Python interface to ISO 639 language codes (parts 1, 2, 3, and 5), allowing you to look up language names and their various standardized code representations.
Provides Python bindings for MeCab-ko, a morphological analyzer for Korean text that segments sentences into morphemes and extracts parts of speech.
PyRuSH segments clinical and telegraphic text into sentences using rule-based hashing, handling abbreviations and formatting irregularities common in medical notes.
Provides stopword lists for multiple languages identified by ISO 639-1 codes, returning them as sets for filtering common words from text processing tasks.
Provides a pre-built Korean morphological analyzer dictionary for mecab-ko, eliminating the need to manually compile mecab-ko and its dictionary.
However, be aware that the package is abandoned and will not receive updates; verify that the pre-built dictionary meets your Korean language processing needs before…
Provides a tree-sitter grammar for parsing CMake code, enabling incremental syntax analysis of CMake files in Python applications.
BabelDOC translates PDF documents between languages, primarily English to Chinese, producing bilingual comparison PDFs with original and translated pages.
Lark-js is a command-line tool that generates standalone LALR(1) parsers in Javascript from Lark grammar files, enabling portable grammar-based parsing across Python, Javascript, and Julia.
Install only if you actively need grammar-based parsing in Javascript.