72 votes
Accepted

How does an AI like ChatGPT answer a question in a subject which it may not know?

ChatGPT is a large language model. That means it's very good at stringing together words in ways that humans tend to use them. It's able to construct sentences that are grammatically correct and sound ...
Mithical's user avatar
  • 2,895
20 votes

How does an AI like ChatGPT answer a question in a subject which it may not know?

ChatGPT does not actually know anything. But more importantly even, it does not know this fact! Hence, it does not know that it does not know. It is only good at combining text.
DrCommando's user avatar
15 votes

How does an AI like ChatGPT answer a question in a subject which it may not know?

ChatGPT and other GPT-based machine learning models don't actually know anything in the sense you're thinking of. ChatGPT is a distant descendant of Markov chain text generators such as Dissociated ...
Mark's user avatar
  • 420
8 votes
Accepted

Why does nobody use decision trees for visual question answering?

For vision tasks, neural network models almost always include a number of layers that pool and convolute. The convolutions, in particular, are very useful - they can make the model generalize better ...
Greenstick's user avatar
7 votes
Accepted

ChatGPT claims that it doesn't get information from anywhere, so can't say why it gave a blatantly false statement. How is that possible?

The reason is that ChatGPT is not a data retrieval system. In other words, it is not consulting a database, nor is it performing searches of the internet, to find answers to questions posed. Instead, ...
David Hoelzer's user avatar
7 votes
Accepted

Can Bayesian inference be combined with knowledge-based systems?

Yes, it is possible to combine probabilistic / bayesian reasoning and a traditional "knowledgebase". And some work along those lines has been done. See, for example, ProbLog ("Probabilistic Prolog") ...
mindcrime's user avatar
  • 3,757
5 votes

How can I translate a natural language question to an MDX query?

You can use a component library which can help you to implement Natural language query builder in your application( the question part ) called Open Natural Language Processing Package , so you can ...
quintumnia's user avatar
  • 1,183
5 votes

How is the F1 score calculated in a question-answering system?

In QA, it's computed over the individual words in the prediction against those in the True Answer. The number of shared words between the prediction and the truth is the basis of the F1 score: ...
Chin Hui Chew's user avatar
3 votes

What are the advantages of Machine Learning compared to traditional programming for developing a chatbot?

In my view ML does not work very well for conversational AI systems. It is generally alright for intent recognition, so getting what the user wants if they ask a question ("I want to book a flight?", "...
Oliver Mason's user avatar
  • 5,397
2 votes

Is there a service that can search for answers to general questions?

You can use Google https://encrypted.google.com/search?hl=en&q=when%20was%20Einstein%20born and parse the response. Wolfram ALPHA is another candidate. http://m.wolframalpha.com/input/?i=what+...
tymtam's user avatar
  • 246
2 votes

How to generate a dataset for question answering from books (like Facebook's bAbI)?

If you are talking about "generating" in the sense of generative models , it is pretty tough. since we are still far beyond understanding the actual structure of question-answering. And even state of ...
thecomplexitytheorist's user avatar
2 votes

What chatbots can answer this type of simple question that only requires to keep track of the context?

I think the issue here is that the chatbots you're using aren't very good at "short-term memory". What I mean by is that the bots construct responses that are slowly and incrementally tuned according ...
Avik Mohan's user avatar
2 votes

Is there a machine learning system that is able to understand mathematical problems given in a textual description?

There was a lot of work on this topic at UT Austin, which has now migrated to the Alan Institute. There is no off-the-shelf software that will answer your question (if there was, DARPA would stop ...
John Doucette's user avatar
2 votes

How does an AI like ChatGPT answer a question in a subject which it may not know?

The original question asked about "an AI" generally, yet most of the responses here focus on OpenAI's ChatGPT specifically. Seems like the answer would depend on the specific type of AI ...
Trutane's user avatar
  • 121
1 vote
Accepted

Why is generative QA + RAG so popular when extractive QA models exist that can provide factual information?

The issue is that extractive QA limits the types of questions to ones that have answers that appear exactly in the text. For example, consider the question: ...
Alexander Wan's user avatar
1 vote

How to disapprove some who says that AI is capable of irrational thought and emotions

AI are based on the idea of distribution matching, no matter what you are doing. Is it a discriminative problem? then match $p_\theta(y|x)$ with the true one, using examples Is it a generative problem?...
Alberto's user avatar
  • 1,677
1 vote

Dynamic text completion

That is achieved usually via web-socket, however it is not available yet I see some workaround like https://github.com/cookeem/chatgpt-service, which just get's the full answer and then streams word ...
Alberto's user avatar
  • 1,677
1 vote

ChatGPT claims that it doesn't get information from anywhere, so can't say why it gave a blatantly false statement. How is that possible?

Incalculable times i caught it literally making things up it does not know. For example an hour ago i asked it if Arnold Schwarzenegger says the line "i don't want to hurt you" in any of his ...
Nix's user avatar
  • 11
1 vote

How to generate a response while considering past questions as well?

What you want to look for is called anaphora resolution. You basically keep a record of the past conversation and try and find an antecedent for any occurrences of it, he/she, her/his, etc. You ...
Oliver Mason's user avatar
  • 5,397
1 vote

Can Facebook's LASER be used like BERT?

LASER creates multilingual contextualized word embeddings, what you do with them is up to you. You can use this as a feature extraction and add whatever you want to the end of the network. I believe ...
Isbister's user avatar
  • 186
1 vote

How to fine tune BERT for question answering?

The answer is yes but 'lightweight' will require a 'lightweight' model. Your application for 'domain one' is called open domain question answering (ODQA). Here is a demonstration of ODQA using BERT: ...
Brian O'Donnell's user avatar
1 vote

Is there a machine learning system that is able to understand mathematical problems given in a textual description?

Well this is a relatively new problem very tied to Question Answering. One of the recent systems is EUCLID that can answer those type of question the public Dolphin algebra question set by using a ...
andres's user avatar
  • 31
1 vote
Accepted

How to generate a dataset for question answering from books (like Facebook's bAbI)?

This repository maintained by Facebook AI Research talks about how they went about generating QA from stories. In essence, they try to simulate how a reader reads a story. They also keep track about ...
Shubham Bhardwaj's user avatar
1 vote

Which parsing algorithm can I use for NLP question answering system?

I have been reading and reading, and found answers to almost all my questions. I am sticking to Earley algorithm, given that it offers a dynamic programming approach (CKY does the same). Both ...
lilienfa's user avatar
  • 319
1 vote

Is there a service that can search for answers to general questions?

You could use dbPedia and/or wikidata. I think Wikidata supports SPARQL now, but don't quote me on that. dbPedia definitely supports SPARQL. If you're not interested in writing SPARQL queries by ...
mindcrime's user avatar
  • 3,757

Only top scored, non community-wiki answers of a minimum length are eligible