Lexical Semantic Resources NLP Tools

Tools and APIs for accessing structured lexical databases, wordnets, and semantic networks across languages. Includes synonym/antonym/hypernym lookup and semantic relationship repositories. Does NOT include word embeddings, word sense disambiguation systems, or semantic parsing tools.

There are 90 lexical semantic resources tools tracked. 1 score above 70 (verified tier). The highest-rated is isaacus-dev/semchunk at 71/100 with 588 stars. 1 of the top 10 are actively maintained.

Get all 90 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=nlp&subcategory=lexical-semantic-resources&limit=20"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

#	Tool	Score	Tier	Stars	Language
1	isaacus-dev/semchunk A fast, lightweight and easy-to-use Python library for splitting text into...	71	Verified	588	Python
2	chatopera/Synonyms :herb: 中文近义词：聊天机器人，智能问答工具包	69	Established	5,104	Python
3	CUNY-CL/wikipron Massively multilingual pronunciation mining	68	Established	363	Python
4	jacksonllee/pylangacq Language Acquisition Research Tools	65	Established	44	Python
5	goodmami/wn A modern, interlingual wordnet interface for Python	65	Established	290	Python
6	UCREL/pymusas Python Multilingual Ucrel Semantic Analysis System	60	Established	36	Python
7	chrislit/abydos Abydos NLP/IR library for Python	57	Established	194	Python
8	mideind/GreynirServer The greynir.is Icelandic natural language processing API and website.	56	Established	67	Python
9	thunlp/OpenHowNet Core Data of HowNet and OpenHowNet Python API	56	Established	635	Python
10	kakaobrain/word2word Easy-to-use word-to-word translations for 3,564 language pairs.	55	Established	369	Python
11	gutfeeling/word_forms Accurately generate all possible forms of an English word e.g "election" -->...	54	Established	632	Python
12	Lilykos/pyphonetics A Python 3 phonetics library.	52	Established	139	Python
13	meta-toolkit/meta A Modern C++ Data Sciences Toolkit	51	Established	712	C++
14	wroberts/pygermanet GermaNet API for Python	51	Established	54	Python
15	natasha/slovnet Deep Learning based NLP modeling for Russian language	51	Established	243	Python
16	soumendrak/openodia This is a package on various tools in the Odia language.	50	Established	7	Python
17	murray-z/text_analysis_tools 中文文本分析工具包（包括- 文本分类 - 文本聚类 - 文本相似性 - 关键词抽取 - 关键短语抽取 - 情感分析 - 文本纠错 - 文本摘要 -...	50	Established	733	Python
18	nlpaueb/gr-nlp-toolkit The Greek NLP toolkit for Python. Supports NER/DP/POS...	48	Emerging	83	Python
19	johnbumgarner/wordhoard This Python module can be used to obtain antonyms, synonyms, hypernyms,...	48	Emerging	126	Python
20	howl-anderson/Chinese_models_for_SpaCy SpaCy 中文模型 \| Models for SpaCy that support Chinese	48	Emerging	673	Jupyter Notebook
21	maxadamski/plwordnet Unofficial Python library for using the Polish Wordnet (plWordNet / Słowosieć)	46	Emerging	21	Python
22	TakeLab/spacy-udpipe spaCy + UDPipe	46	Emerging	167	Python
23	tasdikrahman/vocabulary [Not Maintained anymore] Python Module to get Meanings, Synonyms and what...	46	Emerging	567	Python
24	wetneb/pynif A small Python library for NLP Interchange Format (NIF) for NER(D) systems	46	Emerging	19	Python
25	bureaucratic-labs/revizor Ecommerce product title recognition package	46	Emerging	20	Python
26	mideind/GreynirEngine A fast, efficient natural language processing engine for Icelandic.	45	Emerging	64	Python
27	open-language/en-dictionary En-Dictonary is a node.js module which makes works and their relations...	45	Emerging	13	TypeScript
28	bjascob/pyInflect A python module for word inflections designed for use with spaCy.	43	Emerging	94	Python
29	nltk/wordnet Stand-alone WordNet API	42	Emerging	55	Python
30	Lambda-3/Indra Indra is a Web Service which allows easy access to different distributional...	42	Emerging	49	Java
31	open-language/en-wordnet En-Wordnet is a node.js module which makes Princeton University's Wordnet...	41	Emerging	6	TypeScript
32	dmeoli/WS4J WordNet Similarity for Java provides an API for several Semantic...	39	Emerging	20	Java
33	sdam-au/LAGT ETL repo for ancient Greek texts	39	Emerging	6	Jupyter Notebook
34	open-language/wordnets Wordnets is a gzip package which makes Princeton University's Wordnet and...	38	Emerging	7	TypeScript
35	medzuslovjansky/database Informacija o medžuslovjanskom jezyku: i za kompjutery, i za ljudi	38	Emerging	7	Shell
36	web64/norwegian-nlp-resources Norwegian NLP Resources	38	Emerging	182	—
37	avidale/encodechka The tiniest sentence encoder for Russian language	37	Emerging	246	Python
38	mideind/BinPackage The vocabulary of modern Icelandic, encapsulated in a Python package.	36	Emerging	27	Python
39	slgero/receipt_parser Allow parsing Russian receipts	36	Emerging	54	Python
40	techiaith/lecsicon-cymraeg-bangor Lecsicon cynhwysfawr o eirffurfiau'r Gymraeg yn seiliedig ar ddata gwirydd...	34	Emerging	10	—
41	yweweler/c-t9 A T9 typing system written in C11	33	Emerging	6	C
42	ogpetrov/sakha-nlp Various tools and data for Sakha language NLP.	32	Emerging	5	HTML
43	techiaith/lecsicon-cymraeg-bangor-enghreifftiau Enghreifftiau o ddefnyddio Lecsicon Cymraeg Bangor // Examples of code...	32	Emerging	4	Python
44	melaniab/spacy-pipeline-bg Bulgarian spaCy natural language processing pipeline	31	Emerging	11	HTML
45	ShihabYasin/Extracting-Semantic-Relatedness-For-Bangla-Words Semantic Relatedness For Bangla Words.	31	Emerging	3	Java
46	iis-research-team/wiki-synonyms Python library to search for synonyms in Russian	29	Experimental	6	Python
47	nepalibhasha/varnavinyas वर्णविन्यास — Open-source Nepali orthography toolkit based on Nepal Academy...	29	Experimental	14	Rust
48	ispasic/idiometry An idiom search engine	28	Experimental	8	JavaScript
49	wjbmattingly/spacyex SpaCyEx allows the creation of spaCy Matcher patterns with RegEx like syntax.	28	Experimental	59	Python
50	mattlianje/loquax NLP framework for phonology	28	Experimental	4	Python
51	petra-viola/wortsalat python NLP library for german language	27	Experimental	2	Python
52	BirdsAreFlyingCameras/WordLists A repo containing wordlists I've compiled over time. 215,184 Names, ...	27	Experimental	6	—
53	tech4germany/bam-inclusify INCLUSIFY is a tool to support the practical use of diversity-sensitive...	27	Experimental	12	TypeScript
54	theodm/gender-assistenz Anwendung zur Erkennung von generischem Maskulinum in deutschen Texten und...	27	Experimental	10	Python
55	open-language/id-en-dictionary Id-En-Dictonary is a node.js module which makes Indonesian words, their...	26	Experimental	1	TypeScript
56	Salah-Sal/arabic-wordnet-v4 Arabic WordNet 4.0 - 109,823 synsets translated from Open English WordNet	24	Experimental	—	Python
57	diyclassics/la_core_web_lg spaCy-compatible sm/md/lg/trf core models for Latin, i.e pipeline with POS...	23	Experimental	12	Jupyter Notebook
58	snizio/italian-wiktionary-parser This repository contains a python script for parsing an xml dump of the...	23	Experimental	9	Python
59	wimarka-uic/WiMarka Python library and CLI tool designed for evaluating machine translations...	23	Experimental	2	Python
60	cadia-lvl/icelandic-NLP-resources Overview of Icelandic NLP resources at a glance	23	Experimental	18	—
61	nanguoshun/StatNLP-Framework C++ based implementation of StatNLP framework	23	Experimental	17	C++
62	Nousheen0329/daimones-community Explore AI-driven philosophical dialogues with Aristotle using Ancient...	22	Experimental	—	—
63	pagesjaunes/spacy-french-models French models for spacy	22	Experimental	22	—
64	Aatlantise/prosody-syntax-interface Measuring syntactic information content in prosodic features	22	Experimental	—	Python
65	theodm/gtagger Ergänzedes Projekt zum Projekt gender-assistenz zum manuellen Taggen von...	21	Experimental	1	Python
66	hinrikur/IceNLPy A Python wrapper for the Java-based IceNLP toolkit for Icelandic	20	Experimental	5	Lex
67	shirayu/ita-corpus-chuwa Chunked word annotation for ITA corpus	20	Experimental	5	Python
68	ayzem88/data-analyzer أداة متقدمة لتحليل النصوص العربية بشكل شامل مع إمكانيات متعددة للتحليل...	20	Experimental	1	Python
69	osama-ata/siwar-api 📚 Non-official Python wrapper for the Siwar Arabic Lexicon API...	19	Experimental	3	Python
70	techiaith/geiriau-mwyaf-aml Rhestrau geiriau mwyaf aml y Gymraeg a Saesneg // Wordlists of the most...	19	Experimental	4	—
71	sakelariev/bulgarian-spacy-models Bulgarian models for spaCy – tokenizer, trainable lemmatizer, POS tagger,...	19	Experimental	4	Python
72	imgeyuez/TafIn--Tagger-for-Intensifiers A model which can be used for an automatic identification of intensifiers of...	18	Experimental	2	Python
73	perfah/RSR Refined Semantic Relatedness (RSR), a distributional semantics model.	17	Experimental	1	Java
74	giannirizzola/database-italiano-enigmistica-e-linguistica database-italiano-enigmistica-e-linguistica	15	Experimental	—	—
75	latincy/latincy-guidelines Annotation guidelines for LatinCy Latin NLP models	14	Experimental	1	—
76	Popravljam/serbian-word-explorer Language exploration tool for Serbian linguistics with dictionary search and...	14	Experimental	3	Python
77	eubinean/idiomify Exploring the Efficacy of Idiomify: How Effective is GPT-3 for Teaching...	14	Experimental	16	Python
78	Urdatorn/grc-macronizer Automatic annotation of Ancient Greek vowel length	12	Experimental	1	Python
79	sbdzdz/ivr-synsets Using Polish wordnet to build expanded synsets for an IVR system.	12	Experimental	7	C++
80	ekotwick/aeide NLP project to get my computer to read, parse, and scan lines of ancient...	11	Experimental	3	JavaScript
81	Zaaim-Halim/Arabic_WordNet_Python3 arabic WordNet for python3	11	Experimental	3	Python
82	anka335/information-theory Implementations of information theory algorithms	11	Experimental	—	C++
83	Sion1225/sorpus Sentence OpeRations Processing UtilitieS.	11	Experimental	—	Python
84	ayushmukati08/tcp-dictionary-server A multi-threaded TCP client–server dictionary implemented in Python using...	11	Experimental	—	Python
85	diyclassics/la_senter Repository for training spaCy-compatible sentence segmenter for Latin	11	Experimental	3	Python
86	open-language/id-wordnet Id-Wordnet is a node.js module which makes Bahasa Wordnet available as a package.	11	Experimental	—	TypeScript
87	lggruspe/word2ipa Word-to-IPA transcriptions extracted from Wiktionary.	11	Experimental	3	Python
88	amasotti/AncientGreek_NLP Collections of tools for Ancient Greek (NLP, cleaning etc..)	11	Experimental	3	Jupyter Notebook
89	lirondos/pylazaro A Python library for lexical borrowing detection in Spanish, with a focus on...	10	Experimental	2	Python
90	petar-popovic-bg/Jerteh This package provides utility classes and static methods for Python that...	10	Experimental	2	Python