Got a Question?
Can't find what you're looking for? Ask it here!
- 11 Topics
- 31 Replies
What we are looking for?Something similar to https://try.expert.ai/document-classification/iptc but with custom taxonomies Are custom taxonomies only possible with Studio?Based on my readings, it appears custom taxonomies can only be defined using Studio.The thread above is a few months old, is it still true? Is there a documentation / guide on how to use the Studio? Basically, we want to take the results once the content / document is processed on given taxonomies, use it to provide appropriate suggestions to the end user. This could be easier with a REST API, not sure how Studio could help here. Any pointers?
I have frequently noticed that when I upload documents to the Platform, often the docs are treated and rejected as not being English. For example, in the attached screenshot, the very short document is rejected because the engine considers the NL to be French when it is clearly English: “Adoptive cruise control allows excessive acceleration when vehicle detection clears.” Is there a configuration that I should change to remedy this? Is there a way to override the engine so this doesn’t happen? Thanks!
Thanks for reading. I’m wondering why, when I manually annotate a document in Platform, my annotation is treated as an FN. I would think that, because I hand curated the annotation, it would be considered a TP an FN means an incorrect indication of the absence of a condition when it is actually present. I’m referring to 1) a condition is present and 2) I approve it by annotating, yet the system seems to override my decision-making process. If I annotate a term or phrase and I’ve ensured it’s in the right class, I expect a green TP. I have attached an example where I found a corporate entity, “ONEOK,” that I manually annotated because it belongs to a certain class. However, rather than being indicated by green, as a TP, it is purple. Since this is factored into Experiment scores, it seems like a) I am being penalized for taking the time to manually annotate a document and b) the machine is overriding what I have done as an SME.I hope this makes sense. Perhaps I need a better under
Hi Community.I’m brand new to Studio and working through the intro videos. Currently stuck at step 2 on building rules “Use the KEYWORD attribute in your categorization rule.” https://docs.expert.ai/studio/latest/101/work-with-c-rules/I’ve made a simple rule that looks for a keyword in my text document and Built the module - which completes successfully. As soon as try to analyse the document I get the error below (see image)Analyze Document XXX.txt failed ( - Rules not compiled)There is no where I can find guidance on compiling the rules. Any suggestions as I’m obviously missing something?Many thanks for any help!
Hi All,I was looking through various resources and blog posts from Expert.ai to find out any use cases in Inventory management.I would like to know if Expert.ai platform can check invoices from suppliers as many are paper based. if there is a platformfor matching the invoice with the supplier using taxonomies.Please let me know if you need any further information.Appreciate it if I can get a response by Thursday Morning. Cheers,Venkat
Hi Community users,I would like to know whether there are any use cases/blogs/resources available for expert.ai in the Retail space.Also, would like to know the information related to any projects/demos that expert.ai is/has in the retail industry.Appreciate your response.
So on the developer demo one can input a URL, for example a media article, and the demo would scrape the relevant text from the URL and return the analysis. From what I see in the API docs only the actual text should be submitted - am I missing something or do I need to scrape the text from the URL myself?When I send a URL I get empty results in the return. In the developer demo this does work and scrapes the URL successfully.
I tried to comment on this post: https://community.expert.ai/sentiment-opinion-mining-natural-language-api-hackathon-2021-57/have-questions-about-working-with-the-nl-api-get-answers-during-our-live-q-a-may-20-123?postid=213#post213 but it was not possible. Not sure if it is a permission issue for new users on something else.I tried it on Firefox and Google Chrome, turned off ad blockers, and turned off my VPN but stil not possible. But anyway it’s “Joey Ramone”.
Already have an account? Login
Login to the community
No account yet? Create an account
Enter your username or e-mail address. We'll send you an e-mail with instructions to reset your password.