We present a new release of the Czech-English parallel corpus CzEng. CzEng 1.6 consists of about 0.5 billion words ("gigaword") in each language. The corpus is equipped with automatic annotation at a deep syntactic level of representation and alternatively in Universal Dependencies. Additionally, we release the complete annotation pipeline as a virtual machine in the Docker virtualization toolkit.

We present our submission to the WMT18 Multimodal Translation Task. The main feature of our submission is applying a selfattentive network instead of a recurrent neural network. We evaluate two methods of incorporating the visual features in the model: first, we include the image representation as another input to the network; second, we train the model to predict the visual features and use it as an auxiliary objective. For our submission, we acquired both textual and multimodal additional data. Both of the proposed methods yield significant improvements over recurrent networks and self-attentive textual baselines.

Europe is a multilingual society, in which dozens of languages are spoken. The only op tion to enable and to benefit from multilingual ism is through Language Technologies (LT), i. e., Natural Language Processing and Speech Technologies. We describe the European Lan guage Grid (ELG), which is targeted to evolve into the primary platform and marketplace for LT in Europe by providing one umbrella plat form for the European LT landscape, includ ing research and industry, enabling all stake holders to upload, share and distribute their ser vices, products and resources. At the end of our EU project, which will establish a legal en tity in 2022, the ELG will provide access to ap prox. 1300 services for all European languages as well as thousands of data sets.

Following upon the last year's CUNI system for automatic post-editing of machine translation output, we focus on exploiting the potential of sequence-to-sequence neural models for this task. In this system description paper, we compare several encoder-decoder architectures on a smaller-scale models and present the system we submitted to WMT 2017 Automatic Post-Editing shared task based on this preliminary comparison. We also show how simple inclusion of synthetic data can improve the overall performance as measured by an automatic evaluation metric. Lastly, we list few example outputs generated by our post-editing system.

This work presents our ongoing research of unsupervised pretraining in neural machine translation (NMT). In our method, we initialize the weights of the encoder and decoder with two language models that are trained with monolingual data and then fine-tune the model on parallel data using Elastic Weight Consolidation (EWC) to avoid forgetting of the original language modeling tasks. We compare the regularization by EWC with the previous work that focuses on regularization by language modeling objectives. The positive result is that using EWC with the decoder achieves BLEU scores similar to the previous work. However, the model converges 2-3 times faster and does not require the original unlabeled training data during the finetuning stage. In contrast, the regularization using EWC is less effective if the original and new tasks are not closely related. We show that initializing the bidirectional NMT encoder with a left-toright language model and forcing the model to remember the original left-to-right language modeling task limits the learning capacity of the encoder for the whole bidirectional context.