University of Rochester WMT 2017 NMT System Submission
نویسندگان
چکیده
We describe the neural machine translation system submitted by the University of Rochester to the Chinese-English language pair for the WMT 2017 news translation task. We applied unsupervised word and subword segmentation techniques and deep learning in order to address (i) the word segmentation problem caused by the lack of delimiters between words and phrases in Chinese and (ii) the morphological and syntactic differences between Chinese and English. We integrated promising recent developments in NMT, including back-translations, language model reranking, subword splitting and minimum risk tuning.
منابع مشابه
Multi-source Neural Automatic Post-Editing: FBK's participation in the WMT 2017 APE shared task
Previous phrase-based approaches to Automatic Post-editing (APE) have shown that the dependency of MT errors from the source sentence can be exploited by jointly learning from source and target information. By integrating this notion in a neural approach to the problem, we present the multi-source neural machine translation (NMT) system submitted by FBK to the WMT 2017 APE shared task. Our syst...
متن کاملThe Edit Distance Transducer in Action: The University of Cambridge English-German System at WMT16
This paper presents the University of Cambridge submission to WMT16. Motivated by the complementary nature of syntactical machine translation and neural machine translation (NMT), we exploit the synergies of Hiero and NMT in different combination schemes. Starting out with a simple neural lattice rescoring approach, we show that the Hiero lattices are often too narrow for NMT ensembles. Therefo...
متن کاملVariable Mini-Batch Sizing and Pre-Trained Embeddings
This paper describes our submission to the WMT 2017 Neural MT Training Task. We modified the provided NMT system in order to allow for interrupting and continuing the training of models. This allowed mid-training batch size decrementation and incrementation at variable rates. In addition to the models with variable batch size, we tried different setups with pre-trained word2vec embeddings. Asid...
متن کاملTilde's Machine Translation Systems for WMT 2017
The paper describes Tilde’s EnglishLatvian and Latvian-English machine translation systems for the WMT 2017 shared task in news translation. Both constrained and unconstrained systems are described. Our constrained systems were ranked as the best performing systems according to the automatic evaluation results. The paper gives details to how we pre-processed training data, the NMT system archit...
متن کاملExtending hybrid word-character neural machine translation with multi-task learning of morphological analysis
This article describes the Aalto University entry to the English-to-Finnish news translation shared task in WMT 2017. Our system is an open vocabulary neural machine translation (NMT) system, adapted to the needs of a morphologically complex target language. The main contributions of this paper are 1) implicitly incorporating morphological information to NMT through multi-task learning, 2) addi...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2017