Machine Translation at Booking.com: Journey and Lessons Learned
نویسندگان
چکیده
We describe our recently developed neural machine translation (NMT) system and benchmark it against our own statistical machine translation (SMT) system as well as two other general purpose online engines (statistical and neural). We present automatic and human evaluation results of the translation output provided by each system. We also analyze the effect of sentence length on the quality of output for SMT and NMT systems.
منابع مشابه
Important Lessons Learned From Nearly a Half-Century of Orthopedic Practice
“Those who cannot remember the past are condemned to repeat it” [1]. The famous quote from Hispanic American philosopher George Santayana reminds us of the critical importance of constantly reflecting on the most important lessons garnered from both our own personal experiences and those of our peers. In 49 years of academic orthopedic practice, I have frequently reflected on the most important...
متن کاملRegionalization of the Iowa State University Extension System: Lessons Learned by Key Administrators
The cyclical economic downturn in the United States has forced many Extension administrators to rethink and adjust services and programming. The Cooperative Extension System (CES), the organization primarily responsible for governmental Extension work in the United States, at Iowa State University responded to this economic downturn by restructuring its organization from county based to a regio...
متن کاملLessons learned (and questions raised) from an interdisciplinary Machine Translation approach
Linked Open Data (LOD) has ultimate benefits in various fields of computer science and especially the large area of Natural Language Processing (NLP) might be a very promising use case for it, as it widely relies on formalized knowledge. Previously, the author has published a fast-forward combinatorial approach he called “Semantic Web based Machine Translation” (SWMT), which tried to solve a co...
متن کاملToward a full-scale neural machine translation in production: the Booking.com use case
While some remarkable progress has been made in neural machine translation (NMT) research, there have not been many reports on its development and evaluation in practice. This paper tries to fill this gap by presenting some of our findings from building an in-house travel domain NMT system in a large scale E-commerce setting. The three major topics that we cover are optimization and training (i...
متن کاملMachine Translation of TV Subtitles for Large Scale Production
This paper describes our work on building and employing Statistical Machine Translation systems for TV subtitles in Scandinavia. We have built translation systems for Danish, English, Norwegian and Swedish. They are used in daily subtitle production and translate large volumes. As an example we report on our evaluation results for three TV genres. We discuss our lessons learned in the system de...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- CoRR
دوره abs/1707.07911 شماره
صفحات -
تاریخ انتشار 2017