Machine translation at eBay is developed with the primary goal of facilitating cross-border trade. We design, train, and prepare for production dedicated systems for translation of user search queries, item/product titles on the search result pages and item descriptions. Our MT systems leverage state-of-the-art technology, including statistical models for phrase-to-phrase translation, machine learning algorithms, as well as hybridization through combination with hand-crafted rules for translating and/or preserving named entities such as numbers and product brands.
We build customized, domain-adapted systems which are trained on parallel corpora that contain both eBay-relevant data and automatically crawled web data from the eCommerce domain. The systems are able to utilize both sentence-level and topic-level context in order to disambiguate between different word meanings and translation alternatives. At the same time, the MT systems we build are optimized to work in real-time, yielding high-quality translations within milliseconds. This is especially important for translation of user queries.
eBay's MT group has developed dedicated e-commerce domain systems for translating Russian, Portuguese, Spanish, Italian, French, German into English and vice versa, as well as systems for translating between German and other main European languages. We also have high-quality MT systems for translating Arabic and Chinese. Besides expanding the language coverage, the current work of the MT group focuses on topic or product category adaptation, as well as incorporating explicit and implicit user feedback to improve the user experience with our translations. We also actively explore deep learning methods, including neural network based machine translation.