Search Results for "source"
Sort By:
Showing 61 open source projects for "source"
View related business solutions-
Earn up to 16% annual interest with Nexo.Put idle assets to work with competitive interest rates, borrow without selling, and trade with precision. All in one platform. Geographic restrictions, eligibility, and terms apply.
-
Go From AI Idea to AI App FastAccess Gemini 3 and 200+ models. Build chatbots, agents, or custom models with built-in monitoring and scaling.
-
1
OPolyglot
Your Private Offline Translator
...OPolyglot is an excellent assistant for reading foreign documents, playing games, or working with unlocalized applications, all while keeping your data completely secure. snap: https://snapcraft.io/opolyglot window: https://sourceforge.net/projects/opolyglot/files/v0.1.2/opsetup.exe/download source code: https://github.com/fenenko/OPolyglot -
2
GrammarChecker
Grammar checker for any text field via keyboard shortcut using LLM
GrammarChecker is a utility for instant grammar correction in any text field via keyboard shortcut, powered by Large Language Models (LLM). Grammar Checker utilizes the OpenAI API, supporting both OpenAI and Google Gemini models (It is possible to add other custom models via config), and requires an API key to function. Simply select the text you want to check and trigger the assigned shortcut. Grammar Checker can be automatically launched on startup and run in the system tray. The main... -
3
XBNF library
Neurotranslator grammar librairies
Library providing real-life XBNF grammars. All ressources about XBNF neurotranslator compiler here : https://neurotranslator.sourceforge.io -
4
Thinknowlogy
The world's only naturally intelligent knowledge technology
...Natural language and spatial information are sources of natural intelligence: - Natural language is providing concrete logic for organizing knowledge objects, - Spatial information provides concrete logic for organizing spatial objects (utilized in, e.g., self-driving cars). In this way, our brains know how to organize their knowledge and spatial information. I focus on natural language because this source of natural intelligence is hardly understood by scientists. Hence, the inability of Large Language Models to organize changes in their knowledge independently. -
Full-stack observability with actually useful AI | Grafana CloudBuilt on open standards like Prometheus and OpenTelemetry, Grafana Cloud includes Kubernetes Monitoring, Application Observability, Incident Response, plus the AI-powered Grafana Assistant. Get started with our generous free tier today.
-
5
XBNF Neurotranslator compiler
(X)BNF simple and clever translation grammar compiler
XBNF Neurotranslator is a powerfull extended BNF grammar language to handle translations easily and many features to handle different kind of situations. This project is for common arch binaries, C++ sources, tests & support tickets. No installation, juste get binary for your architecture : > See [Files] > binary.{version} Library of smart samples of grammars> https://sourceforge.net/projects/xbnf/ Docker image which embeds the Linux/64bits binary and the... -
6
Crow Translate
Lightweight translator that allows you to translate and speak text
Crow Translate is a simple and lightweight translator written in C++ / Qt that allows you to translate and speak text using Google, Yandex, Bing, LibreTranslate and Lingva translate API. You may also be interested in my library QOnlineTranslator used in this project. Wayland does not support global shortcuts registration, but you can use D-Bus to bind actions in the system settings. For desktop environments that support additional applications actions (KDE, for example) you will see them... -
7
Apertium: Machine Translation Toolbox
The free and open-source rule-based machine translation platform
Apertium is a toolbox to build open-source shallow-transfer machine translation systems, especially suitable for related language pairs: it includes the engine, maintenance tools, and open linguistic data for several language pairs. -
8
Safe Harbor Deidentification
Safe Harbor Deidentification for medical documents
Phalanx - Deidentify Safe Harbor Deidentification Mode of Phalanx is an abridged pipeline of NLP annotators culminating in NER annotators which write output of text offsets. It uses the Safe Harbor deidentification method. -
9
Arabic Corpus
Text categorization, arabic language processing, language modeling
The Arabic Corpus {compiled by Dr. Mourad Abbas ( http://sites.google.com/site/mouradabbas9/corpora ) The corpus Khaleej-2004 contains 5690 documents. It is divided to 4 topics (categories). The corpus Watan-2004 contains 20291 documents organized in 6 topics (categories). Researchers who use these two corpora would mention the two main references: (1) For Watan-2004 corpus ---------------------- M. Abbas, K. Smaili, D. Berkani, (2011) Evaluation of Topic Identification Methods on... -
Build Securely on AWS with Proven FrameworksMoving to the cloud brings new challenges. How can you manage a larger attack surface while ensuring great network performance? Turn to Fortinet’s Tested Reference Architectures, blueprints for designing and securing cloud environments built by cybersecurity experts. Learn more and explore use cases in this white paper.
-
10
concordia
Powerful search library, best suited for computer-aided translation
Concordia - Roman goddess of agreement. Concordance searcher - tool for translators who need their translations to "agree" with one standard. Concordia is a C++ library for fast text lookup in large corpora. It uses a RAM stored index, which takes up approximately 600MB of memory for a corpus of 2 million sentences. It is based on the idea of a suffix array, enhanced by the presence of other auxiliary data structures. The effects are stunning - Concordia is able to do simple substring... -
11
Presage
the intelligent predictive text entry platform
Presage (formerly Soothsayer) is an intelligent predictive text entry system. Presage generates predictions by modelling natural language as a combination of redundant information sources. Presage computes probabilities for words which are most likely to be entered next by merging predictions generated by the different predictive algorithms. Presage's modular and extensible architecture allows its language model to be extended and customized to utilize statistical, syntactic, and semantic... -
12
Fresh Memory
Flashcards application with Spaced Repetition method
Fresh Memory is an application that helps to learn large amounts of any material with Spaced Repetition method. The most important subject is learning foreign words, but Fresh Memory can be also used to learn anything else. The learning data is stored as flash cards and dictionaries. The flash cards may have several fields, and the user controls what combination of fields to learn. The flashcards can have formatted text and images. -
13
OpenGIA
General Intelligence Algorithm
-
14
The Helsinki Finite-State Transducer toolkit is intended for processing natural language morphologies. The toolkit is demonstrated by wide-coverage implementations of a number of languages of varying morphological complexity.
-
15
OpenNLC
Natural Language Compiler
-
16
poliqarp2
natural language corpora search engine
This project aims at building an efficient indexer and search engine for natural language corpora with multilevel annotations. -
17
Marcion
The study environment of ancient languages (Coptic, Greek, Latin)
Marcion is a software forming a study environment of ancient languages (esp. Coptic, Greek, Latin) and providing many tools and resources (dictionaties, grammars, texts). Although Marcion is focused on to study the gnosticism and early christianity, it is an universal library working with various file formats and allowing to collect, organize and backup texts of any kind. Overview of gnostic sources in Coptic language delivered with Marcion: Nag Hammadi Library; Berlin Codex; Codex... -
18
VoynichReader
Voynich Manuscript viewer.
Software for viewing, searching & analysing Prof. Stolfi's interlinear transcription of the Voynich Manuscript. -
19
Phrasal
Statistical phrase-based machine translation system
Stanford Phrasal is a state-of-the-art statistical phrase-based machine translation system, written in Java. At its core, it provides much the same functionality as the core of Moses. Distinctive features include: providing an easy to use API for implementing new decoding model features, the ability to translating using phrases that include gaps (Galley et al. 2010), and conditional extraction of phrase-tables and lexical reordering models. Developed by The Natural Language Processing Group... -
20
Hebrew Deflector
A proram to de-inflect modern Hebrew words
Hebrew Deflector tries to guess the root, the pattern and the form of a modern Hebrew word provided by the user. It uses the existing rules of the language to do that, and displays the list of possible answers. It is not a dictionary and it doesn't know whether the word (and the listed forms of it) exists or not. It also doesn't know anything about exception to the rules. -
21
Cross-platform application aimed at helping users to learn vocabulary from any foreign language(s). Add/Edit/Delete vocab words (w/ translation, category, sentence, notes, picture). Review (Quiz) vocabulary words.
-
22
bnf2xml
simple BNF parser makes xml markup of matches
bnf2xml a simple BNF parser that takes text as input, searches according to a BNF query file, and outputs text marked up by the xml labels that show context. bnf2xml is as simple to use as any text binary ie, awk(1) grep(1). bnf2xml does not require C API because it outputs simple xml labeling. README is visible on file dl page. EXAMPLE: $ echo "hi" | bnf2xml patternfile <word><alph>h</alph><alph>i</alph></word> or <gas>hydrogen iodide</gas> patternfile says how to find... -
23
Software for speech research. It includes programs and libraries for signal processing, along with general purpose scientific libraries. Most of the code is in Python, with C/C++ supporting code. Also, contains code releases corresponding to publishe
-
24
C++ template library for modular construction of factored probabilistic time-series models, model trainers, and recognizers.
-
25
This tool is made to score machine translation performance with the TER metric. This code is based on Snover's algorithm.
