## losimons

### Profile
- **Name**: lore.simons  
- **Location**: Leuven (Belgium)  
- **LinkedIn**: [linkedin.com/in/lore-simons-37a781122/](https://www.linkedin.com/in/lore-simons-37a781122/)

### About Me
- ML Engineer (focused on NLP, intrigued by a lot more)  
- Self-made software developer  
- Design Sprint Advocate  
- Passionate about Sports  
- “Measuring is knowing”  
- “Practice what you preach”

### Discussions

#### [A chatbot for people suffering from PTSD](https://forum.rasa.com/t/a-chatbot-for-people-suffering-from-ptsd/40150/2)  
*Feb 13, 2021*  
Hi there! Sounds like an interesting use case, curious to your work! Rasa has a couple of useful resources to get started (with developing, or understanding the basics of Natural Language Processing). From the top of my head I would refer you to their [Youtube channel](https://www.youtube.com/c/RasaHQ/videos), it has some great content.

#### [Rasa test nlu: test if all entities are labeled correctly within a sentence](https://forum.rasa.com/t/rasa-test-nlu-test-if-all-entities-are-labeled-chorrectly-within-a-sentence/40134/2)  
*Feb 12, 2021*  
Hi there! Maybe some suggestions. You could “re-process” the .json files generated by the rasa test nlu yourself in a custom script (by combining the DIETClassifier_report.json & DIETClassifier_errors.json you could extract some metrics).

#### [Advice on generating the right amount of NLU training data](https://forum.rasa.com/t/advice-on-generating-the-right-amount-of-nlu-training-data/12401/11)  
*Feb 11, 2021*  
Fair point! I fully understand what you are saying and believe that looking at the actual data/results and ideally taking end-user experience into account is the best way to go. However, in this case, I was just looking for inspiration, if there is a way to get a first view on the performance already.

#### [How to handle 2 numerical slots in 1 form?](https://forum.rasa.com/t/how-to-handle-2-numerical-slots-in-1-form/37354/13)  
*Jan 20, 2021*  
Thank you for all the replies, got something working now! However, I was trying to create some test data to check the performance and I noticed something strange, potentially it has to do with the fact that I am using Duckling to extract numbers and at the same time using roles.

#### [Error when running rasa test even when intent is correct](https://forum.rasa.com/t/error-when-running-rasa-test-even-when-intent-is-correct/37650/3)  
*Dec 15, 2020*  
So this way of entity annotation \[Madrid\]{ "entity" : "location"} will cause an error then? Should it always be \[Madrid\](location)? What if you are working with roles/groups when it comes to entities, for example: {"entity":"number","role":"..."}

#### [Introduce yourself!](https://forum.rasa.com/t/introduce-yourself/25/369)  
*May 4, 2020*  
Hi there! Curious about your work in the STT field! Maybe we could connect through Linkedin? (also based in Belgium by the way 🙂)

#### [Using real chat logs for training?](https://forum.rasa.com/t/using-real-chat-logs-for-training/3637/9)  
*May 2, 2020*  
Hello Martine, out of curiosity: Did you find any solution for your problem? Many thanks, Lore.

#### [Deploy bot on Heroku](https://forum.rasa.com/t/deploy-bot-on-heroku/15867/15)  
*Apr 6, 2020*  
Hi [@cityhunter25197](https://forum.rasa.com/u/cityhunter25197), did you find a solution? Also looking into deploying my rasa chatbot to heroku server, but not sure where to start actually.