Custom components for third party tokenization and entity extraction - Getting Started with Rasa / Tutorials, Resources & Videos - Rasa Community Forum
👋 Introducing the Rasa Playground
Custom components for third party tokenization and entity extraction
post by Tanja on Aug 20, 2019
izhangzhihao implemented two custom components that we wanted to share with the community. You can find the implementation here: GitHub - izhangzhihao/rasa-contrib: Third party conponents of rasa
The first component tokenizes a text by making a request to an external server. Thus, you can, for example, set up a Standford CoreNLP server and use the component of izhangzhihao to get incoming text tokenized by Standford CoreNLP. The other component does the same for entity extraction. You can extract entities from a text using a third party extractor that is called via a HTTP request.
post by gcgloven on Aug 20, 2019
Thx for sharing this! Hope one day I can contribute like this as I learn more about NLP and software design~ ><
Related topics
| Topic | Replies | Views | Activity |
|---|---|---|---|
| Specify component input in RASA NLU | 1 | 725 | Jun 2019 |
| Try my custom components and importers for Rasa | 0 | 490 | Feb 2021 |
| Getting tokens from database | 0 | 217 | Dec 2021 |
| ENTITY EXTRACT WITHOUT FORM | 0 | 218 | Nov 2021 |
| Adding custom entity extraction to my pipeline | 2 | 1.2k | Jan 2020 |