Career Profile

A combination of academic and professional experience in Natural Language Processing, Machine Translation, Computer-Aided Translation, front end and back end development, and app development. Other areas of interest include Language Acquisition, Semantic Web and Linked Data, Knowledge Managment and Machine Learning. Love languages and multilingualism. 🌍 🈸

Experience

Translator and Computational Linguist

2009 - Present
United Nations

Currently working as a translator and have been involved in the development, support and maintenance of several language technology projects at Department of General Assembly and Conference Management, United Nations.

Areas: Compter Aided Translation, Machine Translation and Terminology.

PhD Candidate, Linguistics

2011 - Present
City University of New York, New York

Finished my Master's degree in May 2015, currently doing my PhD. My areas of research include:

  • Automatic Syntactic Parsing
  • Prosody and Sentence Processing
  • Language Acquisition
  • Sentence and Word Alignment, Machine Translation
  • Information Extraction
  • Projects

    As part of my PhD and professional experience, I developed the following systems:

    Tranquility - A simple system for translation quality (Currently English-Arabic)
    Country Sorting Tool - For translating country names and sorting them alphabetically in the target language (Currently English-Arabic)
    Autom8 - A tool to automate several lookup functions to save time for translators.
    Canvas Alignment System - A sentence alignment system to align multilingual documents.
    Multilingual Crawler - A web crawler and search engine to identify, extract and align pages in different languages from multilingual websites listed in Common Crawl
    Extracting Time Information from YAGO - Exploration of YAGO database for havesting machine-readable general knowledge facts.
    Hatchepsut Parser - [IN Progress] A parser for English sentences

    Presentations

  • CIRCL, CUNY, New York, 2017 - Debugging Chomsky's Heirarchy - Adequacy of Context Free Grammar to represent language
  • JIAMCATT, UNHQ, New York, 2015 - Data from Documents, Terminology from Text (my part starts at 28:00)
  • SQUID , City University of New York, 2015 - "He kicked the barrel" - Idioms-based Learnability Model
  • SQUID , City University of New York, 2014 - Templates in Linguistics - Why Garbage Garbage?
  • Wikimania, Alexandria, Egypt, 2008 - Building Arabic Engineering Knowledge
  • Papers

  • Hussein Ghaly and Michael Mandel. "Analyzing Human and Machine Performance In Resolving Ambiguous Spoken Sentences." Proceedings of the Workshop on Speech-Centric Natural Language Processing. 2017.
  • Hussein Ghaly. Canvas: A fast and accurate geometric sentence alignment system using lexical cues within complex misalignment settings. Masters Thesis. City University of New York, 2014.
  • Michelle Morales , David Guy Brizan, Hussein Ghaly, Thomas Hauner, Min Ma, Syed Reza, and Andrew Rosenberg. "Application of Social Network Analysis in the Estimation of Bank Financial Strength During the Financial Crisis."
  • Tutorials

  • My Tutorials Blog: 🔜  My tutorials in different fields
  • Arcompling Community: created community for learning computational linguistics topics related to Arabic language.
  • Trados and Multiterm: created a Youtube tutorial for the easy integration between Trados, Multiterm and Excel
  • Innovation Challenges Won

    Skills & Proficiency

    Python

    Natural Language Processing (NLTK, regex and others)

    Unicode and handling non-Latin characters

    Databases (MySQL, MS SQL Server, and Python Shelve)

    Server Side Scripting (Python CGI)

    Javascript, jQuery & CreateJS

    HTML5 & CSS

    Autohotkey

    Phonegap and Phonegap Build

    Wordpress, Joomla, Wikis & other CMS

    Praat

    Machine Learning (Sklearn, NLTK classifiers, Vowpal Wabbit)

    XML, RDF & OWL

    C#

    PHP

    Angular.js

    MATLAB

    Visual Basic

    AutoCAD

    Node.js