Extending hybrid word-character neural machine translation with multi-task learning of morphological analysis
نویسندگان
چکیده
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) adding an attention mechanism to the character-level decoder, combined with character segmentation of names, and 3) a new overattending penalty to beam search.
منابع مشابه
Hybrid Word-Character Neural Machine Translation for Modern Standard Arabic
Traditional neural machine translation architectures use a word-level approach that assumes all important words have enumerable and relatively frequent surface forms. This assumption is invalid for the large number of non-analytic languages that form new words on the basis of complex morphological processes. Contributing to the quest of finding a universalist architecture that performs well for...
متن کاملAchieving Open Vocabulary Neural Machine Translation with Hybrid Word-Character Models
Nearly all previous work on neural machine translation (NMT) has used quite restricted vocabularies, perhaps with a subsequent method to patch in unknown words. This paper presents a novel wordcharacter solution to achieving open vocabulary NMT. We build hybrid systems that translate mostly at the word level and consult the character components for rare words. Our character-level recurrent neur...
متن کاملAbu-MaTran at WMT 2016 Translation Task: Deep Learning, Morphological Segmentation and Tuning on Character Sequences
This paper presents the systems submitted by the Abu-MaTran project to the Englishto-Finnish language pair at the WMT 2016 news translation task. We applied morphological segmentation and deep learning in order to address (i) the data scarcity problem caused by the lack of in-domain parallel data in the constrained task and (ii) the complex morphology of Finnish. We submitted a neural machine t...
متن کاملCharacter-Level Neural Translation for Multilingual Media Monitoring in the SUMMA Project
The paper steps outside the comfort-zone of the traditional NLP tasks like automatic speech recognition (ASR) and machine translation (MT) to addresses two novel problems arising in the automated multilingual news monitoring: segmentation of the TV and radio program ASR transcripts into individual stories, and clustering of the individual stories coming from various sources and languages into s...
متن کاملWord, Subword or Character? An Empirical Study of Granularity in Chinese-English NMT
Neural machine translation (NMT), a new approach to machine translation, has been proved to outperform conventional statistical machine translation (SMT) across a variety of language pairs. Translation is an open-vocabulary problem, but most existing NMT systems operate with a fixed vocabulary, which causes the incapability of translating rare words. This problem can be alleviated by using diff...
متن کامل