Registry

Module Specifications

Current Academic Year 2012 - 2013
Please note that this information is subject to change.

Module Title	Statistical Machine Translation
Module Code	CA446
School	School of Computing
Online Module Resources
Module Co-ordinator	Semester 1: Jennifer Foster Semester 2: Jennifer Foster Autumn: Jennifer Foster
NFQ level	8	Credit Rating	0
Pre-requisite	None
Co-requisite	None
Compatibles	None
Incompatibles	None

Description

This course introduces the fundamentals of statistical machine translation.

Learning Outcomes

1. Understand the challenges associated with machine translation
2. Understand the noisy channel model underpinning statistical machine translation
3. Demonstrate how a statistical translation model can be inferred from a parallel corpus of text using unsupervised machine learning techniques
4. Explain the concept of statistical language modelling and how it fits in to the basic SMT architecture
5. Understand the concept of decoding and be in a position to implement a basic beam decoder
6. Evaluate a statistical machine translation system using at least one automatic metric
7. Understand the state-of-the-art in statistical machine translation
8. Familiar with the open-source Moses toolkit

Workload	Full-time hours per semester
*Type*	*Hours*	*Description*
Total Workload: 0

All module information is indicative and subject to change. For further information,students are advised to refer to the University's Marks and Standards and Programme Specific Regulations at: http://www.dcu.ie/registry/examinations/index.shtml

Indicative Content and Learning Activities

None

Assessment Breakdown
Continuous Assessment	50%	Examination Weight	50%

Course Work Breakdown
Type	Description	% of total	Assessment Date
Project	Students undertake a group project of their choosing which involves training a machine translation system using the open-source Moses toolkit.	50%	n/a

Reassessment Requirement
Resit arrangements are explained by the following categories; 1 = A resit is available for all components of the module 2 = No resit is available for 100% continuous assessment module 3 = No resit is available for the continuous assessment component
This module is category 3

Indicative Reading List