laserembeddings
marian-dev
laserembeddings | marian-dev | |
---|---|---|
2 | 4 | |
223 | 247 | |
- | 0.0% | |
0.0 | 6.6 | |
9 months ago | 2 months ago | |
Python | C++ | |
BSD 3-clause "New" or "Revised" License | GNU General Public License v3.0 or later |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
laserembeddings
-
Firefox Translations doesn't use the cloud
You're pretty much right on the money. For ParaCrawl[1] (which I worked on) we used fast machine translation systems that were "good enough" to translate one side of each pair to the language of the other, see whether they'd match sufficiently, and then deal with all the false positives through various filtering methods. Other datasets I know of use multilingual sentence embeddings, like LASER[2], to compute the distance between two sentences.
Both of these methods have a bootstrapping problem, but at this point in the MT for many languages we have enough data to get started. Previous iterations of ParaCrawl used things like document structure and overlap of named entities among sentences to identify matching pairs. But this is much less robust. I don't know how they solve this problem today for low-resource languages.
[1] https://paracrawl.eu
[2] https://github.com/yannvgn/laserembeddings
-
SpaCy v3.0 Released (Python Natural Language Processing)
I've been using LASER from Facebook Research via https://github.com/yannvgn/laserembeddings to accept multi-lingual input in front of the the domain-specific models for recommendations and stuff (that are trained on English annotated examples).
marian-dev
-
Firefox Translations doesn't use the cloud
As far as I could tell this is the engine powering this:
https://github.com/marian-nmt/marian-dev/
It’s compiled c++ running using wasm.
-
Official Firefox add-on bringing offline translation support to Firefox
This is the underlying translation engine:
https://github.com/marian-nmt/marian-dev
And the browser fork of it:
https://github.com/browsermt/marian-dev
-
Mozilla releases local machine translation tools as part of Project Bergamot
You can find the engine used here [1], the API built around it here [2] and its WASM port here [3] and the WebAssembly matrix multiplication optimizations are here [4]
[1] https://marian-nmt.github.io/
What are some alternatives?
syntaxdot - Neural syntax annotator, supporting sequence labeling, lemmatization, and dependency parsing.
bergamot-translator - Cross platform C++ library focusing on optimized machine translation on the consumer-grade device.
spaCy - 💫 Industrial-strength Natural Language Processing (NLP) in Python
marian - Fast Neural Machine Translation in C++
BLINK - Entity Linker solution
firefox-translations - Firefox Translations is a webextension that enables client side translations for web browsers.
wiktextract - Wiktionary dump file parser and multilingual data extractor
firefox-translations-training - Training pipelines for Firefox Translations neural machine translation models
projects - 🪐 End-to-end NLP workflows from prototype to production
berga-translator - A browser extension that provides client-sided translation via the Bergamot Project
duckling - Language, engine, and tooling for expressing, testing, and evaluating composable language rules on input strings.
tagtransfer - Evaluations for tag-transfer in bergamot