This article is the second in a series of articles on how to use the DeepL translation API, and introduces file translation. (The first article can be found here.) *Rudimentary knowledge of Python and Linux is assumed. Translating Text Files Now that we have warmed up, let's try file translation. This one requires a combination of three API calls. Please prepare a text file test.txt containing appropriate Japanese...

In this article, we will show you how to use the DeepL translation API in the first and second parts, one for string translation and the other for file translation. *A rudimentary knowledge of Python and Linux is assumed. Please also refer to the original manual. https://www.deepl.com/en/docs-api Python uses 3.9. API specifications are current as of July 2022. Please be advised. AP...

Interview with a person in charge of "kode-AI Translation Cloud API" about machine learning and evaluation (Part 2)! This article is the second part of the series. ～This article is a continuation of the first part of the blog. 3. evaluation results - what is BLEU value? ～ 3. evaluation results - what is the BLEU value? ～ Satake: Before and after machine learning 10,000 cases of data, another 1,000 cases of data that were not directly ...

Contents (Part 1) 1. What is machine learning for neural engines? 2. Introduction to the evaluation procedure of machine learning results Hello everyone! It's been a while (;^ω^) here at the Kohden Development Office blog. In this blog, our sales representative, Mr. Satake, interviews our developers and introduces various development and product information in a conversational style. Today's interviewee is this person! Mr. Shibata is currently studying Chinese, Korean, and Russian. (Before...

Performance Verification of a Field-Specific NMT Engine I made a field-specific neural machine translation engine - I actually made a prototype of a field-specific Japanese-Chinese/Chinese-Japanese NMT engine using the Chinese-Japanese bilingual data in the IT field that I collected in "Focusing on Data Collection and Performance Verification (Part 1)". To create the model of the translation engine, we used a tool called OpenNMT. In the following sections, we will actually translate a test sentence (in the IT field) to see how the IT field NMT performs....