고객이 서비스하는 언어를 대규모 학습 데이터 기반으로 여러 나라의 언어로 자동 번역해 줍니다
Statistical-based Machine Translation API Utilizing Large-scale Learning Data
The Statistical Machine Translation (SMT) technology is a statistics-based machine translation technology with the strength to translate newly-coined words and phrases, due to faster translation speed and a vast amount of vocabulary it can translate. It breaks a sentence down into words or phrases to provide the translation that is deemed statistically to be the most natural.
- Rich Language Processing Experience
- More accurate and natural translations can be achieved by applying NAVER's technology and experience on multi-language processing to a translation engine. By taking into account feedback on the translation quality accumulated through NAVER’s services, it has addressed the shortcomings of the existing technology that relies only on statistics.
- Building Various Learning Databases
- It has a large-scale learning data that makes natural translations possible. To strengthen the core translation technology capable of effectively identifying language rules, a high-quality learning model is employed.
- Easy Use
- Web-based console allows convenient and easy usage. The RESTful-type APIs allow simple and easy application of translation features on your services.
Provides a range of artificial intelligence services that learns from NAVER's abundant data.
Once input text is sent using a RESTful API method, this API recognizes the text from the server and returns text translated
into another language.
Translation is available in three languages: English, Japanese, and Chinese (Simplified and Traditional).
Using the API
As an open API that does not require a login, service usage is possible by sending the Client ID and the Client Secret value issued when you registered the application in the HHTP header at the time of calling POST.
Currently, this API is utilized in several services by NAVER, such as translation of NAVER entertainment news, Grafolio
comments, and V live subtitles.
Furthermore, the LINE Translation Bot, which provides translation services in twenty languages, is armed with Papago's SMT technology.
Notes for Use
- Papago SMT can only translate short sentences, which means that it requires the user to input text and then returns translated text.
- Translations that include HTML tags are referred as 'web translation' and this feature is currently not supported.
- The maximum number of characters you can enter at a time is 5,000. (including spaces)
Service Usage Limit
You can adjust the usage limit of Papago SMT yourself using various options from 3 million characters a month (100,000 characters a day) to 300 million characters a month (100 million characters a day) per application.
Calling is allowed for the last call that exceeds the usage limit. (The usage fee is calculated based on the number of actual calls.)
E.g., you have set the monthly usage limit to 1,000 characters. Once you use 990 characters, you can call an extra 20 characters. Then, you can use a total of 1010 characters and will be billed for 1010 characters.
If you need to increase the service limit, please contact Customer Support.
|Billing Units||Usage Fee|
|1,000,000 characters||10,000 KRW/1,000,000 characters|
- A service fee is charged every 1,000,000 characters. Therefore, the number of characters input for translation is
rounded up to the nearest 1,000,000 characters for calculation.
(E.g., If you use 500,000 characters, then you will be charged 10,000 KRW and if you use 1,600,000 characters, then you will be charged 20,000 KRW.)
- The number of characters includes spaces.
- The usage (number of characters) is calculated on a monthly basis and the remaining characters are not carried forward to the next month.