New Language Pairs in TectoMT

By Ondrej Dusek, Luís Manuel dos Santos Gomes, Michal Novák, Martin Popel, Rudolf Rosa. 2015

15 citations recorded by the source corpus.

The TectoMT tree-to-tree machine translation system has been updated this year to support easier retraining for more translation directions. We use multilingual standards for morphology and syntax annotation and language-independent base rules. We include a simple, non-parametric way of combining TectoMT’s transfer model outputs. We submitted translations by the Englishto-Czech and Czech-to-English TectoMT pipelines to the WMT shared task. While the former offers a stable performance, the latter is completely new and will require more tuning and debugging.

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

In Natural Language Processing

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).”
Sequence-to-Sequence Generation for Spoken Dialogue via Deep Syntax Trees and Strings (2016, methodology): “We present a new, conceptually simple NLG system for SDS that is able to operate in both modes: it either produces natural language strings or generates deep syntax dependency trees, which are subsequently processed by an external surface realizer (Dušek et al., 2015).”