TectoMT: Highly Modular MT System with Tectogrammatics Used as Transfer Layer
By Zdenek Zabokrtský, Jan Ptácek, Petr Pajas. 2008
124 citations recorded by the source corpus.
We present a new English→Czech machine translation system combining linguistically motivated layers of language description (as defined in the Prague Dependency Treebank annotation scenario) with statistical NLP approaches.
Subfields: Artificial Intelligence, Natural Language Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Ondrej Bojar
- Ondrej Dusek
- Eneko Agirre
- Gorka Labaka
- Filip Jurvc'ivcek
- Graham Neubig
- Tom Kocmi
- Roman Sudarikov
In Natural Language Processing
- Ondrej Bojar
- Ondrej Dusek
- Filip Jurvc'ivcek
- Eneko Agirre
- Gorka Labaka
- Rudolf Rosa
- Roman Sudarikov
- Tom Kocmi
Citations in the corpus
- Neural Generation for Czech: Data and Baselines (2019, methodology): “Further works using multilingual rule-based surface realization pipelines were developed in the context of machine translation (Aikawa et al., 2001; ˇZabokrtsk´y et al., 2008; Duˇsek et al., 2015).”
- New Language Pairs in TectoMT (2015, methodology): “TectoMT (Žabokrtský et al., 2008) is a tree-to-tree MT system system consisting of an analysis-transfer-synthesis pipeline, with transfer on the level of deep syntax.”
- Further Meta-Evaluation of Machine Translation (2008, neutral): “CU-TECTOMT Charles University TectoMT (Zabokrtsky et al., 2008)”
- CUNI Submissions in WMT18 (2018, methodology): “These tables were added to the Chimera2016 sys-tem, which already had one phrase table from genuine parallel data and one synthetic phrase table from TectoMT ( ˇZabokrtsk´y et al., 2008) output.”
- SMT and Hybrid systems of the QTLeap project in the WMT16 IT-task (2016, methodology): “The Czech synthesis pipeline has remained basically unchanged since the original TectoMT system ( ˇZabokrtsk´y et al., 2008).”