The course covers the area of machine translation (MT) in its current breadth, delving deep enough in each approach to let you confuse every existing MT system. We put a balanced emphasis on several imporant types of state-of-the-art systems: phrase-based MT, surface-syntactic MT and (a typically Praguian) deep-syntactic MT. We do not forget common pre-requisities and surrounding fields: extracting translation equivalents from parallel texts (including word alignment techniques), MT evaluation or methods of system combination.
We aim to provide a unifying view of machine translation as statistical search in a large search space, well supported with practical experience during your project work in a team or alone. Finally, we also attempt to give a gist of emerging approaches in MT, such as neural networks.
All lecture materials since 2008 are available in the course SVN:
For read-only access use username: student and password: student
Metrics of MT Quality.
Approaches to MT. Statistical MT. Phrase-Based MT. Moses.
Parallel texts. Sentence and word alignment. hunalign, GIZA++.
Morphology in MT. Factored phrase-based translation. Moses.
Model optimization (MERT). Moses tools.
Phrase-structure trees in MT. Parsing-based MT. Stat-XFER, Joshua.
Dependency trees in MT.
Tectogrammatical trees in MT. TectoMT.
Advanced: Search. System combination. Neural networks in MT.
Contributions to the grade:
≥50% good, ≥70% very good, ≥90% excellent.