Anaphora Models and Reordering for Phrase-Based SMT
By Christian Hardmeier, Sara Stymne, Jörg Tiedemann, Aaron Smith, Joakim Nivre. 2014
9 citations recorded by the source corpus.
We describe the Uppsala University systems for WMT14. We look at the integration of a model for translating pronominal anaphora and a syntactic dependency projection model for English‐French. Furthermore, we investigate post-ordering and tunable POS distortion models for English‐ German.
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
- Philipp Koehn
- Ondrej Bojar
- Lucia Specia
- Graham Neubig
- Matt Post
- Barry Haddow
- Rico Sennrich
- Christof Monz
In Natural Language Processing
- Philipp Koehn
- Lucia Specia
- Ondrej Bojar
- Barry Haddow
- Matt Post
- Christof Monz
- Rico Sennrich
- Graham Neubig
Citations in the corpus
- Findings of the 2014 Workshop on Statistical Machine Translation (2014, methodology): “Second, we compare these two methods against WMT13’s “Expected Wins” approach, and then select among them by determining which of them has the highest accuracy in terms of predicting annotations on a held-out set of pairwise judgments.”