CUNI NMT System for WAT 2017 Translation Tasks
نویسندگان
چکیده
The paper presents this year’s CUNI submissions to the WAT 2017 Translation Task focusing on the Japanese-English translation, namely Scientific papers subtask, Patents subtask and Newswire subtask. We compare two neural network architectures, the standard sequence-tosequence with attention (Seq2Seq) (Bahdanau et al., 2014) and an architecture using convolutional sentence encoder (FBConv2Seq) described by Gehring et al. (2017), both implemented in the NMT framework Neural Monkey1 that we currently participate in developing. We also compare various types of preprocessing of the source Japanese sentences and their impact on the overall results. Furthermore, we include the results of our experiments with out-of-domain data obtained by combining the corpora provided for each subtask.
منابع مشابه
Tokyo Metropolitan University Neural Machine Translation System for WAT 2017
In this paper, we describe our neural machine translation (NMT) system, which is based on the attention-based NMT (Luong et al., 2015) and uses long shortterm memories (LSTM) as RNN. We implemented beam search and ensemble decoding in the NMT system. The system was tested on the 4th Workshop on Asian Translation (WAT 2017) (Nakazawa et al., 2017) shared tasks. In our experiments, we participate...
متن کاملSMT reranked NMT
System architecture, experimental settings and experimental results of the EHR team for the WAT2017 tasks are described. We participate in three tasks: JPCen-ja, JPCzhja and JPCko-ja. Although the basic architecture of our system is NMT, reranking technique is conducted using SMT results. One of the major drawback of NMT is under-translation and over-translation. On the other hand, SMT infreque...
متن کاملPatent NMT integrated with Large Vocabulary Phrase Translation by SMT at WAT 2017
Neural machine translation (NMT) cannot handle a larger vocabulary because the training complexity and decoding complexity proportionally increase with the number of target words. This problem becomes even more serious when translating patent documents, which contain many technical terms that are observed infrequently. Long et al. (2017) proposed to select phrases that contain out-of-vocabulary...
متن کاملKyoto University Participation to WAT 2016
This paper describes the experiments we did for the WAT 2016 (Nakazawa et al., 2016a) shared translation task. We used two different machine translation (MT) approaches. On one hand, we used an incremental improvement to an example-based MT (EBMT) system: the KyotoEBMT system we used for WAT 2015. On the other hand, we implemented a neural MT (NMT) system that makes use of the recent results ob...
متن کاملComparison of SMT and NMT trained with large Patent Corpora: Japio at WAT2017
Japan Patent Information Organization (Japio) participates in patent subtasks (JPC-EJ/JE/CJ/KJ) with phrase-based statistical machine translation (SMT) and neural machine translation (NMT) systems which are trained with its own patent corpora in addition to the subtask corpora provided by organizers of WAT2017. In EJ and CJ subtasks, SMT and NMT systems whose sizes of training corpora are about...
متن کامل