Open Source Unix Shell Linguistics Software

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 refresh supervision signals. The project also provides scripts to fetch and preprocess monolingual data, learn BPE codes, and train cross-lingual embeddings that bootstrap unsupervised alignment between languages. Beyond the core EMNLP 2018 setup, the codebase exposes additional, optional capabilities such as multi-language training, language model pretraining with shared parameters, and adversarial training.

THIS PROJECT MIGRATED TO https://gitlab.com/mwetoolkit/mwetoolkit3/ The Multiword Expressions toolkit aids in the automatic identification and extraction of multiword units in running text. These include idioms (kick the bucket), noun compounds (cable car), phrasal verbs (take off, give up), etc. Even though it focuses on multiword expresisons, the framework is quite complete and can also be useful in any corpus-based study in computational linguistics. The mwetoolkit can be applied to virtually any text collection, language, and MWE type. It is a command-line tool written mostly in Python. Its development started in 2010 as a PhD thesis but the project keeps active (see the SVN logs). Up-to-date documentation and details about the tool can be found on the mwetoolkit website: http://mwetoolkit.sourceforge.net/

Aelius is an ongoing open source project aiming at developing a suite of Python, NLTK-based modules and interfaces to external freely available tools for shallow parsing of Brazilian Portuguese. It also includes language resources such as language models, sample texts, and gold standards. Presently, Aelius already offers facilities for POS-tagging and chunking corpora and outputting annotations in different formats, such as in XML in the TEI P5 encoding scheme.

Affisix is a program for automatic recognition of prefixes. It takes large amount of words and according to the user setting it tries to determine which segments of these words are prefixes.

Various tools for creating annotated parallel corpora including pre-trained tagging and parsing models for various languages, sentence alignment tools and word alignment tools. Uplug also includes a web-based interface for interactive sentence and word alignment and scripts for indexing and querying parallel corpora using the Corpus Work Bench CWB. Download 'uplug-main' first and then add other packages.

Migrado a GithUB EN: https://github.com/christiangda/es-ve La mejor opción para verificar y corregir la gramática de tus documentos de LibreOffice escritos en español. La extensión incluye: Corrector Ortográfico, Tesauro de Sinónimos y Separación Silábica. ¡Hecho en Venezuela! Sus principales características son: Más DE 87.000 lemas y sus respectivas conjugaciones. Contiene el Lemario actualizado de RAE (Real Academia Española) Términos financieros e informáticos aceptados por RAE Nombres de Países, sus abreviaciones y capitales Contiene el Lemario actualizado NoRAE (Que no se encuentran en la Real Academia Española y son muy utilizados) Nombres de la División Político Territorial Venezolana(Estados, Municipios y Parroquias) Nombres de las capitales de Estados y sus

Summary: Your eyes are tired of looking into the tablet or cell-phone screen reading ebooks? You have difficulty reading from LCD screen specially in a driving vehicle? This software is for you! It converts your PDF files to MP3 audio books. Special Features (Compared to similar projects): Each page is in a separate MP3 file. Created MP3 files have ID3v2 tags showing Book name and page number. Multi-threaded conversion, means all CPU cores will be used thus multiple times faster conversion.

Implementing an Open Source search engine, based on sphinx and nutch. The aim of this project is to provide an open free alternative to Google. A particular work will be done on french. BTW this project will help students and engineers to understand how a search engine works. Feel free to contact us