Multi-Source Neural Model for Machine Translation of Agglutinative Language
نویسندگان
چکیده
منابع مشابه
Machine Translation of the Ural-altaic as an Agglutinative Language
In this paper we present the results of Korean to Japanese translation in especial from the machine translation system between Korean and Japanese language which have linguistic properties and similarities strongly in Syntax or Phraseology as the Ural-Altaic languages. For its implementation, we have developed syntax based machine translation system KANT designed to be capable of multi-lingual ...
متن کاملEncoding Source Language with Convolutional Neural Network for Machine Translation
The recently proposed neural network joint model (NNJM) (Devlin et al., 2014) augments the n-gram target language model with a heuristically chosen source context window, achieving state-of-the-art performance in SMT. In this paper, we give a more systematic treatment by summarizing the relevant source information through a convolutional architecture guided by the target information. With diffe...
متن کاملMulti-granularity Word Alignment and Decoding for Agglutinative Language Translation
Lexical sparsity problem ismuchmore serious for agglutinative language translation due to the multitude of inflected variants of lexicons. In this paper, we propose a novel optimization strategy to ease spareness bymulti-granularity word alignment and translation for agglutinative language. Multiple alignment results are combined to catch the complementary information for alignments, and rules ...
متن کاملSyllable-level Neural Language Model for Agglutinative Language
Language models for agglutinative languages have always been hindered in past due to myriad of agglutinations possible to any given word through various affixes.We propose a method to diminish the problem of out-of-vocabulary words by introducing an embedding derived from syllables and morphemes which leverages the agglutinative property. Our model outperforms character-level embedding in perpl...
متن کاملEnsemble Learning for Multi-Source Neural Machine Translation
In this paper we describe and evaluate methods to perform ensemble prediction in neural machine translation (NMT). We compare two methods of ensemble set induction: sampling parameter initializations for an NMT system, which is a relatively established method in NMT (Sutskever et al., 2014), and NMT systems translating from different source languages into the same target language, i.e., multi-s...
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: Future Internet
سال: 2020
ISSN: 1999-5903
DOI: 10.3390/fi12060096