Wmt ’ 17
نویسندگان
چکیده
This paper describes LIMSI’s submissions to the news shared task at WMT’17 for English into Czech and Latvian, as well as related experiments. This year’s novelties consist in the use of a neural machine translation system with a factored output predicting simultaneously a lemma decorated with morphological information and a fine-grained part-of-speech. Such a type of system drew our attention to the specific step of reinflection, where lemmas and parts-of-speech are transformed into fully inflected words. Finally, we ran experiments showing an efficient strategy for parameter initialization, as well as data filtering procedures.
منابع مشابه
XMU Neural Machine Translation Systems for WMT 17
This paper describes the Neural Machine Translation systems of Xiamen University for the translation tasks of WMT 17. Our systems are based on the Encoder-Decoder framework with attention. We participated in three directions of shared news translation tasks: English→German and Chinese↔English. We experimented with deep architectures, different segmentation models, synthetic training data and ta...
متن کاملAdaptive working memory training improved brain function in human immunodeficiency virus–seropositive patients
OBJECTIVE We aimed to evaluate the effectiveness of an adaptive working memory (WM) training (WMT) program, the corresponding neural correlates, and LMX1A-rs4657412 polymorphism on the adaptive WMT, in human immunodeficiency virus (HIV) participants compared to seronegative (SN) controls. METHODS A total of 201 of 206 qualified participants completed baseline assessments before randomization ...
متن کاملLIMSI Submission for WMT'17 Shared Task on Bandit Learning
This paper describes LIMSI participation to the WMT’17 shared task on Bandit Learning. The method we propose to adapt a seed system trained on out-domain data to a new, unknown domain relies on two components. First, we use a linear regression model to exploit the weak and partial feedback the system receives by learning to predict the reward a translation hypothesis will get. This model can th...
متن کاملMaintaining Gait Performance by Cortical Activation during Dual-Task Interference: A Functional Near-Infrared Spectroscopy Study
In daily life, mobility requires walking while performing a cognitive or upper-extremity motor task. Although previous studies have evaluated the effects of dual tasks on gait performance, few studies have evaluated cortical activation and its association with gait disturbance during dual tasks. In this study, we simultaneously assessed gait performance and cerebral oxygenation in the bilateral...
متن کاملEvaluating the morphological competence of Machine Translation Systems
While recent changes in Machine Translation state-of-the-art brought translation quality a step further, it is regularly acknowledged that the standard automatic metrics do not provide enough insights to fully measure the impact of neural models. This paper proposes a new type of evaluation focused specifically on the morphological competence of a system with respect to various grammatical phen...
متن کامل