In this paper, we present a straightforward strategy for transferring dependency parsers across languages. The proposed method learns a parser from partially annotated data obtained through the projection of annotations across unambiguous word alignments. It does not rely on any modeling of the reliability of dependency and/or alignment links and is therefore easy to implement and parameter free. Experiments on six languages show that our method is at par with recent algorithmically demanding methods, at a much cheaper computational cost. It can thus serve as a fair baseline for transferring dependencies across languages with the use of parallel corpora.

This paper describes the joint submission of the QT21 and HimL projects for the English→Romanian translation task of the ACL 2016 First Conference on Machine Translation (WMT 2016). The submission is a system combination which combines twelve different statistical machine translation systems provided by the different groups (RWTH Aachen University, LMU Munich, Charles University in Prague, University of Edinburgh, University of Sheffield, Karlsruhe Institute of Technology, LIMSI, University of Amsterdam, Tilde). The systems are combined using RWTH's system combination approach. The final submission shows an improvement of 1.0 BLEU compared to the best single system on newstest2016.

Because the most common transition systems are projective, training a transition-based dependency parser often implies to either ignore or rewrite the non-projective training examples, which has an adverse impact on accuracy. In this work, we propose a simple modification of dynamic oracles, which enables the use of non-projective data when training projective parsers. Evaluation on 73 treebanks shows that our method achieves significant gains (+2 to +7 UAS for the most nonprojective languages) and consistently outperforms traditional projectivization and pseudoprojectivization approaches.

We present PanParser, a Python framework dedicated to transition-based structured prediction, and notably suitable for dependency parsing. On top of providing an easy way to train state-of-the-art parsers, as empirically validated on UD 2.0, PanParser is especially useful for research purposes: its modular architecture enables to implement most state-of-the-art transition-based methods under the same unified framework (out of which several are already built-in), which facilitates fair benchmarking and allows for an exhaustive exploration of slight variants of those methods. PanParser additionally includes a number of fine-grained evaluation utilities, which have already been successfully leveraged in several past studies, to perform extensive error analysis of monolingual as well as cross-lingual parsing.

This paper describes LIMSI's submissions to the shared WMT'16 task "Translation of News". We report results for Romanian-English in both directions, for English to Russian, as well as preliminary experiments on reordering to translate from English into German. Our submissions use mainly NCODE and MOSES along with continuous space models in a post-processing step. The main novelties of this year's participation are the following: for the translation into Russian and Romanian, we have attempted to extend the output of the decoder with morphological variations and to use a CRF model to rescore this new search space; as for the translation into German, we have been experimenting with source-side pre-ordering based on a dependency structure allowing permutations in order to reproduce the target word order.