What is custom glossary setting/custom glossary model?

The process of wrapping the standard model of MT learning service or the custom trained model registered in this system using a glossary to automatically output the translation defined in the glossary is called “Custom glossary setting” in this system (sometimes called "Glossary wrapping"). As the result of custom glossary setting, a custom glossary model is created. Once the custom glossary setting has been completed, the models set with glossaries can be used in Quick MT/PE of this system.

Information in Custom Glossary Model Registration screen

In this screen, you can register a new custom glossary model. The general steps are as follows:

1. Select the model type for which you want to set a glossary.
   
   • Standard MT model: Sets the glossary against the standard (generic) model of a MT learning service.
   • Custom trained model: Sets the glossary against a custom trained model registered in LAC.
2. If you select 'Standard MT model' in Step 1, choose a MT learning service for which you want to perform the custom glossary setting. With this system, you can use the following three MT learning services. When selecting "Kawamura NMT", please additionally select one of the types (see below section).
   
   • Google AutoML
   • Kawamura NMT
   • Amazon Translate
3. If you select 'Custom trained model' in Step 1, choose one from the custom trained models registered in your organization. Press [Custom Trained Model] button to display a selection window. You can specify criteria to search for the models that have been completed the custom training. Turn on the radio button for the model you want to use and press [OK] button. You can select only one custom trained model.
4. Once you select a target model, select a glossary you want to set against the model. Press [Select Glossary] button to display the selection window. You can specify criteria to search for the language assets (glossaries only) that have been imported. Turn on the radio button for the glossary you want to use and press the [OK] button. You can select only one glossary. When you selected a custom trained model, select a glossary in the same language direction. If you want to select a glossary whose language direction is reversed, tick [Reverse language] checkbox in the next step.
5. The main screen displays a list of the selected language glossary. If you want to reverse the language direction of the glossary at setting a glossary, select [Reverse language] checkbox.
6. When all settings are completed, click [Glossary Setting Request] button. The custom glossary setting is scheduled to run and will appear in Custom Glossary Model list. Registration of the custom glossary models may take hours to complete, depending on the size of the provided glossary, load on MT learning services, and so on.

About Kawamura NMT engine type

There are eight types of models (combinations of types and language pairs) for Kawamura NMT. The characteristics of each type are listed below. Please select the one that best suits your purpose.

• General NT: Engine can be used for the translation in any field/purpose of the source documents.
• Patents NT: Engine built specifically for patent translation, and supports specific terms and phrases.
• Finance Services: Engine built specifically for financial services translation, and supports specific terms and phrases.
• Finance NT (IR/Disclosure): Engine built specifically for the translation of IR/disclosure information related to financial service, and supports specific terms and phrases.
• Legal documents NT: Engine built specifically for the translation of legal documents, and supports specific terms and phrases.
• Science: Engine built specifically for translation in fields suitable for academic papers mainly in biological and medical fields, and supports specific terms and phrases.
• Patent decision etc.: Engine built specifically for the translation of notices of reasons for refusal of patent applications and decision information, etc. among patent-related documents, and supports specific terms and phrases.
• News: Engine built specifically for the translation of news, including new words, new topics and current topics, and supports specific terms and phrases.

Duplicate terms in the glossary

You can register duplicate terms (bilingual data) in the glossary, but it is recommended that a term pair (source-target text) be unique, whether referenced as a glossary or incorporated into a custom glossary model. However, there are cases where you want to change the translation of each term and the translation of a compound word, as shown below.

If you create a custom glossary model with a glossary which includes such bilingual data, when you machine translate the source text (in this case, English) using the model, the term with the longer source length will be prioritized and the translation will be adopted. In the above example, if “asset management” appears in the source text, “アセットマネジメント” will be prioritized as the translation, so this source text will not be output as “資産管理”.

About upper limit of models

If your organization already own a maximum number of custom glossary models, you cannot request glossary setting process. Use one of the following measures to ensure that there is enough room to reach the upper limit.

• Delete some of custom glossary models you have: Please go to Custom Glossary Model List from the navigation menu and delete the models your organization own.
• Increase the Custom Glossary Model Limit: If you do not want to delete any model, you can increase the limit. Please access XMAT Support Contact Form or please contact our sales representative.