Neural Networks Classifier for Data Selection in Statistical Machine Translation
نویسندگان
چکیده
منابع مشابه
Neural Networks Classifier for Data Selection in Statistical Machine Translation
Corpora are precious resources, as they allow for a proper estimation of statistical machine translation models. Data selection is a variant of the domain adaptation field, aimed to extract those sentences from an out-of-domain corpus that are the most useful to translate a different target domain. We address the data selection problem in statistical machine translation as a classification task...
متن کاملAdditive Neural Networks for Statistical Machine Translation
Most statistical machine translation (SMT) systems are modeled using a loglinear framework. Although the log-linear model achieves success in SMT, it still suffers from some limitations: (1) the features are required to be linear with respect to the model itself; (2) features cannot be further interpreted to reach their potential. A neural network is a reasonable method to address these pitfall...
متن کاملDynamic Data Selection for Neural Machine Translation
Intelligent selection of training data has proven a successful technique to simultaneously increase training efficiency and translation performance for phrase-based machine translation (PBMT). With the recent increase in popularity of neural machine translation (NMT), we explore in this paper to what extent and how NMT can also benefit from data selection. While state-of-the-art data selection ...
متن کاملParagraph Vector for Data Selection in Statistical Machine Translation
In this paper, we investigate data selection methods used in domain adaptation for Statistical Machine Translation targeting an in-domain made up of non-standard data, such as transcriptions of spoken data. In data selection, the sentences from the general domain are scored according to their similarity to the in-domain. This research explores Paragraph Vectors as means of scoring sentences fro...
متن کاملSubmodularity for Data Selection in Statistical Machine Translation
We introduce submodular optimization to the problem of training data subset selection for statistical machine translation (SMT). By explicitly formulating data selection as a submodular program, we obtain fast scalable selection algorithms with mathematical performance guarantees, resulting in a unified framework that clarifies existing approaches and also makes both new and many previous appro...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: The Prague Bulletin of Mathematical Linguistics
سال: 2017
ISSN: 1804-0462
DOI: 10.1515/pralin-2017-0027