Timeline for Can I use AI to interpret XML documents?
Current License: CC BY-SA 4.0
19 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| May 13, 2022 at 14:49 | history | edited | nbro | CC BY-SA 4.0 |
deleted 23 characters in body; edited tags; edited title
|
| Feb 7, 2019 at 12:09 | comment | added | Nishant | I am working on a platform which will apply deep learning on XML documents. Please check out my github repo xml.ai. This is a work in progress. Please add a star if you like. | |
| Oct 16, 2018 at 5:39 | vote | accept | DBX12 | ||
| Sep 4, 2017 at 19:33 | answer | added | Oliver Mason | timeline score: 2 | |
| Sep 4, 2017 at 17:45 | answer | added | Thomas Kimber | timeline score: 6 | |
| Sep 4, 2017 at 6:42 | comment | added | DBX12 | @DukeZhou ah, now I understand. I added a sample of a false positive to my example code. In reality, almost all phone numbers are valid and the check if the phone is reachable should be no concern to the AI. | |
| Sep 4, 2017 at 6:37 | history | edited | DBX12 | CC BY-SA 3.0 |
Added false positive sample
|
| Sep 3, 2017 at 21:40 | comment | added | DukeZhou | @DBX12 I was meaning that an AI could go about validating the data, once it identified data needing to be validated, much more quickly than I could by hand (googling a phone number, for instance, to make sure it is associated with the person in question.) | |
| Sep 2, 2017 at 11:26 | comment | added | DBX12 | @DukeZhou Thank you for the welcome. I'm not sure I follow about the "AI could do it much more quickly" part. Do you think an AI wouldn't be faster than a human identifying the correct nodes? | |
| Sep 2, 2017 at 11:23 | comment | added | DBX12 | @antlersoft That was my initial idea. I think I have enough XML schemas at hand (otherwise I will generate some via script from sample data). My line of thought was "Humans can learn to differentiate that. AI can learn like humans so AI should be able to learn this too". But then the question "how to start and are there frameworks?" rose, resulting in this question, | |
| Sep 2, 2017 at 11:19 | comment | added | DBX12 |
@mindcrime The human can make the distinction between, because the data belonging together would be more or less under the same parent. I updated my question with a sample XML. As you can see, the data about one person is below the <foo> parent. For humans it's clear that each <foo> represents one person.
|
|
| Sep 2, 2017 at 11:17 | history | edited | DBX12 | CC BY-SA 3.0 |
added sample XML
|
| S Sep 2, 2017 at 11:06 | history | suggested | quintumnia |
added some tags.
|
|
| Sep 1, 2017 at 20:32 | review | Suggested edits | |||
| S Sep 2, 2017 at 11:06 | |||||
| Sep 1, 2017 at 18:55 | comment | added | antlersoft | I'm guessing that what you really want is an AI that, given an arbitrary XML schema, can guess which elements/attributes the data you want is going to be encoded in. So to train your AI, you would need a large number of different schemas with the correct elements already tagged. | |
| Sep 1, 2017 at 18:27 | comment | added | DukeZhou | Welcome to AI! (I very much like mindcrime's comment, b/c I know how I'd go about validating the information, and suspect an AI could do it much more quickly.) | |
| Sep 1, 2017 at 18:08 | comment | added | mindcrime♦ | The first question I'd ask is "can a human make the distinction you're asking about, and how?" | |
| Sep 1, 2017 at 14:45 | review | First posts | |||
| Sep 1, 2017 at 18:27 | |||||
| Sep 1, 2017 at 14:44 | history | asked | DBX12 | CC BY-SA 3.0 |