Open Source Perl Linguistics Software

Based on the Buckwalter Morphological Analyzer (Version 1.0) for doing Arabic stemming and POS tagging. Includes a rewrite of the original Perl script, with better documentation and more flexible options, and a C++ interface (usable as a library or app).

A minimalist approach to share text documents and data annotations. Allows a large number of different annotations to be represented. Project files contain: - simple code to hold/read/write data and perform sample processing. - BioC-formatted corpora - BioC tools that work with BioC corpora BioC goals - simplicity - interoperability - broad use - reuse There should be little investment required to learn to use a format or a software module to process that format. We are interested in reuse, and we focus on common NLP tasks that are broadly useful for textmining.

Part-of-speech tagging is the task of assigning symbols from a particular set to words in a natural language text. ACOPOST implements and extends well-known machine learning techniques and provides a uniform environment for testing.

The central problem to be addressed in this project concerns a multidisciplinary (linguistics and computational linguistics) investigation into sharing of knowledge and resources between closely-related languages, specifically relating to the automatic processing of compounds. Specifically, we will explore the possibility to create new knowledge about closely-related languages, and efficiently develop additional, more advanced resources for (a) compound segmentation; and (b) the semantic analysis of compounds; as such, the project will be divided into two interrelated subprojects, to be executed simultaneously. The focus in this project will be on Afrikaans (with Dutch as the closely-related, well-sourced language), which will lay grounds for future work on other closely-related language pairs.

This is a Java-based project for complex event extraction from text and co-reference resolution. Currently the code can read BioNLP shared task format (http://2011.bionlp-st.org/) and i2b2 Natural Language Processing for Clinical Data shared task format (https://www.i2b2.org/NLP/DataSets/Main.php). Event extraction includes finding events and the parameters for an event in a text. The method is based on SVM but other ML algorithms can be adopted. The method details are explained in the following paper: Ehsan Emadzadeh, Azadeh Nikfarjam, and Graciela Gonzalez. 2011. Double Layered Learning for Biological Event Extraction from Text. In Proceedings of the BioNLP 2011 Workshop Companion Volume for Shared Task, Portland, Oregon, June. Association for Computational Linguistic

ElixirFM is a high-level implementation of Functional Arabic Morphology. The core of ElixirFM is written in Haskell, while interfaces in Python and Perl support lexicon editing and other interactions. http://github.com/otakar-smrz/elixir-fm

Encode Arabic provides tools for encoding and decoding Arabic in Haskell, Python, Perl, or LaTeX. Interprets the ArabTeX notation to generate original orthography or phonetic transcription. Supports Buckwalter and other romanizations. Converts legacy byte encodings into Unicode. http://github.com/otakar-smrz/encode-arabic

The goal of this project is to investigate optimal ways to do genre classification for the ten indigenous South African languages. Funded by Dept of Arts and Culture of the SA Government. http://www.trifonius.co.za/projects/genre-classification

************************************************************ THIS PROJECT IS MOVED. See http://khcoder.net/en for the latest & greatest. You can download this tool from the new home. See you there! ************************************************************

This project is devoted to the development of natural language processing tools and resources for the Lingala language, which is spoken by tens of millions of people in central Africa.

A database of linguistic annotation of medical text (from MEDLINE), including corpora used with ABGene, BioCreative I and II, and the MedPost training corpus.

This program reads each of 270,000 entries of the BÍN database of ICELANDIC lemmata and all their forms. It assigns one of hundreds of morphological paradigms to each entry. It won a special award in the Þú átt orðið competition (www.ordid.is)

The Parenthesis Classifier takes the contents of a set of parentheses and classifies it into one of several categories. It includes a parenthesized-data extractor and the classifier.

Sample turing machine for educational purposes.

Perstem is a Persian (Farsi) stemmer, morphological analyzer, transliterator, and partial part-of-speech tagger. Inflexional morphemes are separated or removed from their stems. Perstem can also tokenize and transliterate between various character set encodings and romanizations.

This project concerns the development of human language technology resources, based on the approach to share or recycle resources between closely related language. http://gerhard.pro/closely-related-languages/

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.

The Simple Semantic Classifier classifies short chunks of natural language text into broad semantic classes that correspond to the OBO ontologies provided as input.

A sound change applier to simulate phonological shift, as from Latin to Spanish.

hspell - Hebrew spellchecker

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.

ValiTerms is a tool that helps the validation of terms in corpus. It finds their occurrences and allows terminologists to choose if a term is relevant or not. ValiTerms is developed at LIPN (http://www-lipn.univ-paris13.fr), RCLN team. Please consult the wiki for instructions about installation and usage.

This project tries to make Spanish Wikipedia a useful resource for the language research community.

Stance is a perl script for generating random sentences in Dutch, which can be used as translation exercises for students of Dutch. In its finished version, it should be able to generate only gramatically correct sentences.