Stack Overflow
Stack Overflow

Questions tagged [nlp-question-answering]

Question Answering is the computer task of mechanically answering questions posed in natural language. (Please do not use this tag to indicate that you have a question and want an answer. That's already implied.)

For more information, see: https://en.wikipedia.org/wiki/Question_answering

243 questions
0
votes
0 answers

Json file based Question and answering model using VertexAI

I'm working on document based question and answering model using vertexAI.. But here I'm using Json file instead of document such as PDF or DOCS. Consider that, the 1000s of json file which contains the specific customer information. So I need to…
Karthick Pandian
  • 1
  • 1
0
votes
0 answers

Title extraction from the text files

I have large number of text files in different format; few of them are emails. I need to extract their titles. Due to range of formats, the titles are not in the same location in the documents. Sometimes it exists in the middle of the document and…
Aaron
  • 3
  • 3
0
votes
0 answers

NVIDIA NeMO container Intent / Slots Filling training issue

I setup the NVIDIA nvcr.io/nvidia/nemo:23.06 container, started jupyter, I can go through all steps of the notebook Joint Intent and Slot Filling, GPU is recognized but if I run training then only 1 epoch there are any changes, all other epoches the…
Rick
  • 33
  • 6
0
votes
0 answers

Chatbot with camenBert - Not response

Good morning, I'm trying to develop a little bot that can answer questions based on a small knowledge base loaded beforehand in text format. I launch the bot I can ask my question but it only returns the question and the "context" but never an…
demenvil
  • 1,089
  • 1
  • 12
  • 25
0
votes
0 answers

Chat with spreadsheet using meta-llama/Llama-2-13b-chat-hf

I made a spreadsheet which contain around 2000 question-answer pair and use meta-llama/Llama-2-13b-chat-hf model. But when start querying through the spreadsheet using the above model it gives wrong answers most of the time & also repeat it many…
aiwesee
  • 1
0
votes
0 answers

How to handle the language of an LLM response in a specific language?

I have been working on a RAG architecture with the Falcon-40b model and the implementation of the chatbot must be in Spanish. I understand that Falcon-40b is multilingual. So far the RAG has returned good responses but sometimes outputs the response…
Josalo9
  • 23
  • 3
0
votes
1 answer

Is 'examples' a default output variable for HuggingFace transformers library?

I'm running various example code from HuggingFace docs, and a variable examples repeatedly appears in these tutorials. Many functions have it as a formal parameter: def preprocess_function(examples): questions = [q.strip() for q in…
pol0
  • 33
  • 5
0
votes
0 answers

Purpose of using special tokken in DONUT

text in this code they have used special tokken as New special tokens: ['', '', '', '', '', '', '', '', '', ''] and adding via…
shubham bhardwaj
  • 1
  • 2
0
votes
0 answers

How to build a model in Python which will allow me to have discussion(question - answer) with my data which is in csv format?

I have the above dataset. I want to create a model which allows me to ask questions to the data and answers them correctly, my questions are not predefined and depend on the user at that particular time. What should I do ? Example of my questions :…
apurva bhujbal
  • 1
  • 1
0
votes
1 answer

Generating Q&As from Cyrillic languages with Deepset Haystack

I'm trying to generate questions and answers based on an uploaded text. I'm using opensource library Haystack by Deepset in order to do that as it works great with English texts. However, with Cyrillic texts like Russian I get chopped words in the…
user164863
  • 580
  • 1
  • 12
  • 29
0
votes
0 answers

Change a pandas Data Frame to Hugging Face Dataset for Question Answering

I should change a pandas Data Frame to the Hugging Face Dataset object, this will be used in the Question Answering Task and I want to fine-tune the model for further prediction on my custom dataset. The problem is that I just have questions and…
Sahar Y.M
  • 1
0
votes
0 answers

Bert return nan as lost

I am trying to make an model that is trained on custom data to eventually make a chatbot from it. The problem is training the model resolves in loss as nan. I am trying to to train the model and see some sort of loss but this loop breaks and does…
Vicklo
  • 1
0
votes
0 answers

Train T5 on Conversational Machine Comprehension Datasets

I have been trying to fine-tune the T5 model on Conversational Machine Comprehension Datasets with no satisfactory results. Particularly, I have been trying it on QuAC, with unanswerable questions. I am a beginner in NLP tasks and do not know how to…
padfoot96
  • 1
0
votes
1 answer

Updater.__init__() got an unexpected keyword argument 'token'

Updater.__init__() got an unexpected keyword argument 'token' It shows the error when I perform this updater = Updater(token=TOKEN, use_context=True) I got strucked by this error anyone help me to get out of this i can install the version of…
Chukkala Jayanth
  • 1
0
votes
0 answers

Why does my Flask chatbot code take a very long time to execute and does not respond at the 'app.run()' step?

very long time consumed in executing the code and with no response I've tried running the below code many times which is for creating a web application for a custom Q&A chatbot feeded by a custom data, but unfortunately the execution doesn't…
ahmed hamdy
  • 1
  • 2
1 2 3
…
16 17