# \*\* Feature Request. Addition of text processing packages for Japanese + Korean.

**URL:** <https://forum.knime.com/t/feature-request-addition-of-text-processing-packages-for-japanese-korean/76301>\
**Category:** Feedback & Ideas\
**Created:** [December 31, 2023, 1:02pm UTC](https://forum.knime.com/t/feature-request-addition-of-text-processing-packages-for-japanese-korean/76301 "2023-12-31T13:02:39Z")\
**Posts on this page:** 7\
**Page:** 1

<div class="post-metadata">

**Author:** ![umutcankurt](https://forum-cdn.knime.com/user_avatar/forum.knime.com/umutcankurt/32/70644_2.png) [@umutcankurt](https://forum.knime.com/u/umutcankurt)\
**Post date:** [December 31, 2023, 1:02pm UTC](https://forum.knime.com/t/feature-request-addition-of-text-processing-packages-for-japanese-korean/76301/1 "2023-12-31T13:02:39Z")

</div>

I am requesting help on this issue as we are working with data in many different languages, in all languages. I also think that many people will definitely need it in the future.

If you currently have an alternative solution suggestion, please share it.

Thanks.

 ![image](https://forum-cdn.knime.com/uploads/default/original/3X/2/b/2bc7e40d48891ff12847ecac6163a70ff883bc52.png)

---

<div class="post-metadata">

**Author:** ![umutcankurt](https://forum-cdn.knime.com/user_avatar/forum.knime.com/umutcankurt/32/70644_2.png) [@umutcankurt](https://forum.knime.com/u/umutcankurt)\
**Post date:** [December 31, 2023, 5:27pm UTC](https://forum.knime.com/t/feature-request-addition-of-text-processing-packages-for-japanese-korean/76301/2 "2023-12-31T17:27:38Z")

</div>

> **[Pre-Trained NLP Models for Asian Languages](https://www.kaianalytics.com/post/nlp-tools-for-asian-languages)**
>
> May is Asian Heritage Month in Canada (Asian American and Pacific Islander Month in the USA), a month where we celebrate the contributions Asian-Canadians have made and continue to make. While many NLP researchers focus on English, there are some...

> **[GitHub - taishi-i/awesome-japanese-nlp-resources: A curated list of resources...](https://github.com/taishi-i/awesome-japanese-nlp-resources)**
>
> A curated list of resources dedicated to Python libraries, LLMs, dictionaries, and corpora of NLP for Japanese - GitHub - taishi-i/awesome-japanese-nlp-resources: A curated list of resources dedica...

> **[GiNZA: install a Japanese NLP library in one step - Megagon Labs](https://megagon.ai/ginza-install-a-japanese-nlp-library-in-one-step/)**
>
> At Megagon Labs, we strive to enable seamless utilization of Japanese natural language processing (NLP) for engineers and data scientists around the world. We’re proud to announce we’ve taken one big step forward in fulfilling this endeavor. By...

[https://jprocessing.readthedocs.io/en/latest/](https://jprocessing.readthedocs.io/en/latest/)

---

<div class="post-metadata">

**Author:** ![Artem](https://forum-cdn.knime.com/user_avatar/forum.knime.com/artem/32/47971_2.png) [@Artem](https://forum.knime.com/u/Artem)\
**Post date:** [January 2, 2024, 7:52am UTC](https://forum.knime.com/t/feature-request-addition-of-text-processing-packages-for-japanese-korean/76301/3 "2024-01-02T07:52:29Z")

</div>

Hello @umutcankurt

As an alternative you can use [Redfield NLP nodes](https://hub.knime.com/redfield/extensions/se.redfield.textprocessing.feature/latest) that run Spacy under the hood. [Spacy](https://spacy.io/models) is a Python NLP library that supports multiple languages, including Korean and Japanese.

---

<div class="post-metadata">

**Author:** ![umutcankurt](https://forum-cdn.knime.com/user_avatar/forum.knime.com/umutcankurt/32/70644_2.png) [@umutcankurt](https://forum.knime.com/u/umutcankurt)\
**Post date:** [January 2, 2024, 11:05am UTC](https://forum.knime.com/t/feature-request-addition-of-text-processing-packages-for-japanese-korean/76301/4 "2024-01-02T11:05:59Z")

</div>

Hi; @Artem  
Thanks for the answer, I don’t know how to do it but I will try. If you have an example to share, please share it.

My goal is to categorize the texts in the data set according to the reference word and code list.

Actually, I have a working solution and it works very well, you can find it in the attached link. However, I cannot proceed due to the language problem and I am looking for a solution to solve this problem.

> [@Creating the reference category column with the words in the texts in the data list](https://forum.knime.com/t/creating-the-reference-category-column-with-the-words-in-the-texts-in-the-data-list/59428/17):
>
> Hi; @DiaAzul I’ve been working with test data and I’m sending the workflow by email. I couldn’t upload it here because the size is too big. (I worked on the first workflow you posted) Why do you think it gives blank code for some of the matches? I will be glad if you can look at it when you have time

---

<div class="post-metadata">

**Author:** ![Artem](https://forum-cdn.knime.com/user_avatar/forum.knime.com/artem/32/47971_2.png) [@Artem](https://forum.knime.com/u/Artem)\
**Post date:** [January 2, 2024, 11:15am UTC](https://forum.knime.com/t/feature-request-addition-of-text-processing-packages-for-japanese-korean/76301/5 "2024-01-02T11:15:19Z")

</div>

I briefly looked at this thread. And I believe you can just include Redfield NLP nodes in your workflow and use them together with Text Processing nodes. So I guess you can replace the nodes that do the tokenization, lemmatization and different types of tagging with the new ones.

Just to emphasize: Redfield NLP node **are fully compatible** with Text Processing nodes and they also operate on or produce the Document data type.

Here is an example that shows how these nodes work.

> **[Redfield NLP Nodes: Spacy example – artem](https://hub.knime.com/artem/spaces/Public/Spacy_preproc_nodes_fixed~8SXqEBSXQjFLUS75/current-state)**
>
> A simple workflow demostrating how to utilize all Spacy nodes in Knime. The example is given for Portuguese texts from Wikipedia.

---

<div class="post-metadata">

**Author:** ![system](https://forum-cdn.knime.com/uploads/default/original/1X/ab3ccf34482a0329361734a18199390177204f15.png) [@system](https://forum.knime.com/u/system)\
**Post date:** [April 1, 2024, 11:16am UTC](https://forum.knime.com/t/feature-request-addition-of-text-processing-packages-for-japanese-korean/76301/6 "2024-04-01T11:16:03Z")

</div>

This topic was automatically closed 90 days after the last reply. New replies are no longer allowed.

---

<div class="post-metadata">

**Author:** ![ScottF](https://forum-cdn.knime.com/user_avatar/forum.knime.com/scottf/32/61316_2.png) [@ScottF](https://forum.knime.com/u/ScottF)\
**Post date:** [June 5, 2024, 9:06pm UTC](https://forum.knime.com/t/feature-request-addition-of-text-processing-packages-for-japanese-korean/76301/7 "2024-06-05T21:06:54Z")

</div>


