Online shoppers depend on customer reviews when evaluating products or services. However, in the international online marketplace, reviews in a user’s language may not be available. Translation of online customer reviews is therefore an important service. A crucial aspect of this task is translating opinion words, key words that capture the reviewers’ sentiments. This is challenging because opi...

The invited talk concentrates on recent developments in WIPO Translate. We will notably highlight our experience in using Neural Machine Translation (NMT) in production on PATENTSCOPE since September 2016. We describe the training and decoding pipeline, a first quality evaluation experiment (comparing automatic metrics with publically available commercial tools and the impact on post edition) a...

MonoTrans2 is a translation system that combines machine translation (MT) with human computation using two crowds of monolingual source (Haitian Creole) and target (English) speakers. We report on its use in the WMT 2011 Haitian Creole to English translation task, showing that MonoTrans2 translated 38% of the sentences well compared to Google Translate’s 25%.

In order to control computational complexity, neural machine translation (NMT) systems convert all rare words outside the vocabulary into a single unk symbol. Previous solution (Luong et al., 2015) resorts to use multiple numbered unks to learn the correspondence between source and target rare words. However, testing words unseen in the training corpus cannot be handled by this method. And it a...

Improving machine translation (MT) systems with memories (TMs) is of great interest to practitioners in the MT community. However, previous approaches require either a significant update model architecture and/or additional training efforts make models well-behaved when TMs are taken as input. In this paper, we present simple but effective method introduce into neural (NMT) systems. Specificall...

This paper describes the NICT-2 translation system for the 3rd Workshop on Asian Translation. The proposed system employs a domain adaptation method based on feature augmentation. We regarded the Japan Patent Office Corpus as a mixture of four domain corpora and improved the translation quality of each domain. In addition, we incorporated language models constructed from Google n-grams as exter...

The number of Free Online Machine Translation (FOMT) users witnessed a spectacular growth since 1994. FOMT systems change the aspects of machine translation (MT) and the mass translated materials using a wide range of natural languages and machine translation systems. Hundreds of millions of people use these FOMT systems to translate the holy Quran (Al-Qurʾān) verses from the Arabic language to...