Search Results for "commons"

Unsupervised Machine Translation is a research repository that implements both phrase-based SMT and neural MT approaches for translation without parallel corpora. The neural component supports multiple architectures—seq2seq, biLSTM with attention, and Transformer—and allows extensive parameter sharing across languages to improve data efficiency. Training relies on denoising auto-encoding and back-translation, with on-the-fly, multithreaded generation of synthetic parallel data to continually...

CompE Toolkit allows the user to seamlessly convert between binary, decimal, hexadecimal, and 32-bit floating point representation. It uses a simple, user-friendly interface designed for maximum efficiency and minimal clutter.

A small parser for the Esperanto language, intended as an API for other programs. The blog entry describing this program's function and motivation can be found here: http://coder32768.blogspot.com/2014/04/gort-klaatu-barada-esperanto.html The program takes text in Esperanto, and returns an object graph describing that utterance. The program has expansion points for transforms of this graph, in the spirit of transformational grammars.

This is a database of the Arabic roots and their derivatives in voweled and unvoweled forms along with stems. The database is extracted from the well known Arabic legacy dictionary "تاج العروس من جواهر القاموس".

Smulsa 2001 is a multilanguage two-way translator, transliterator, and dictionary. Its dependencies are gambas2-ide & gambas2-gb-db-sqlite. The application needs its database to run properly. Smulsa 2001 adalah penerjemah, pengalih aksara, dan kamus dua arah multibahasa. Dependensinya gambas2-ide & gambas2-gb-db-sqlite. Aplikasi ini memerlukan basisdatanya untuk berjalan dengan baik.