We introduce a simple and accurate neural model for dependency-based semantic role labeling. Our model predicts predicate-argument dependencies relying on states of a bidirectional LSTM encoder. The semantic role labeler achieves competitive performance on English, even without any kind of syntactic information and only using local inference. However, when automatically predicted partof-speech tags are provided as input, it substantially outperforms all previous local models and approaches the best reported results on the English CoNLL-2009 dataset. We also consider Chinese, Czech and Spanish where our approach also achieves competitive results. Syntactic parsers are unreliable on out-of-domain data, so standard (i.e., syntactically-informed) SRL models are hindered when tested in this setting. Our syntax-agnostic model appears more robust, resulting in the best reported results on standard out-of-domain test sets.

This paper describes Yandex School of Data Analysis (YSDA) submission for WMT2016 Shared Task on Quality Estimation (QE) / Task 1: Sentence-level prediction of post-editing effort. We solve the problem of quality estimation by using a machine learning approach, where we try to learn a regressor from feature space to HTER score. By enriching the baseline features with the syntactical features and additional translation system based features, we achieve Pearson correlation of 0.525 on the test set.

No abstract

No abstract

No abstract