Natural Language Processing & Portuguese-Chinese Machine Translation Laboratory (NLP2CT)
自然語言處理與中葡機器翻譯實驗室
Location E11-2023
Academic Staff in charge Prof. Fai WONG, Derek; Prof. Sam CHAO, Lidia
Technician Francisco DE OLIVEIRA; Hok Lam SIO, William
Telephone (853) 8822-2542, 4295, 4285
Open Access Reservation Period Wednesday: 9:00 - 17:00
Laboratory Website http://nlp2ct.cis.umac.mo/

Objective | Facilities | Experiments | Courses supported

 

 

     

Objective

The Natural Language Processing & Portuguese-Chinese Machine Translation Laboratory is established for the purpose of providing working area with facilities for research and development of Natural Language Processing and Machine Translation related areas.

Facilities

Machines

Dell XPS and Optiplex desktop computers

HP Compaq Elite Microtower desktop computers

Platform

Windows, Linux

Printers

HP Laserjet P2015

Scanners

HP Scanjet 5590

Software

Programming Software; Portuguese-Chinese Machine-Aided Translation Systems (PCT Dictionary, PCT Assistente, PCT TransLite); Corpus creation, annotation and management tools; Linguistic Data Consortium Corpora – Treebank-3, Chinese Treebank 7.0

Natural Language Processing and Machine Translation Software

Systems permit students to understand how these could help in the translation work in a more effective way. Moreover, they could have the opportunity to work with real systems and understand better the weaknesses and strengths in this field.

PCT – Portuguese Chinese Bilingual Dictionary

The system is a bilingual dictionary and it has more than 100,000 entries in the database; a simple to use and a trilingual user interface; a mouse-tracking function to retrieve the meaning of a word by pointing it with the mouse; and a Portuguese, Cantonese, and Mandarin pronunciation function.



PCT Bilingual Dictionary Interface



PCT Mouse Tracking Function

PCT Assistente – Portuguese-Chinese Machine Aided Translation System

PCT Assistente provides a simple interface to help users in doing the translation work, which is embedded in Microsoft Word environment. The system provides five main functions: the selection of the knowledge base to suit different subject needs; interactive translation with the participation of users; automatic translation to generate preliminary translations on the fly; show and hide to display the translated result against the original sentence; commit function to retain all the revised bilingual pairs to the knowledge base.



PCT Assistente Translation Interface

PCT TransLite

The system is mainly used for education purpose. Users are provided a simple interface to insert simple bilingual grammars and perform the translation based on the constructed grammar. Moreover, they could also review the tree structure of the sentence translated.



PCT TransLite Interface

Corpus creation, annotation and management tools

The system enables users to create, manually check, and modify the translation result before assigning a final annotation to the syntax tree and storing the results back to the database.



Corpus Annotation and Management System

Experiments

  1. Implementation of simple Natural Language Processing Tools
  2. Practice in translating documents with the help of Machine-Aided Translation Tools
  3. Analysis, Construction and Annotation of Syntax Trees with bilingual information

Courses supported

CISB220 Compiler Construction
CISB454 Introduction to Natural Language Processing
CISB410 Final Year Project
SFTW341 Compiler Construction
SFTW462 Introduction to Natural Language Processing
SFTW496 Final Year Project
COIS719 Machine Translation
COIS723 Applied Natural Language Processing
IMSS019 Machine Translation
IMSS999 Thesis
COIS823 Advanced Topics in Computer Science