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
1
vote
1 answer

ModuleNotFoundError: No module named 'haystack.nodes'

I am following the tutorial from haystacks website for Extractive QA system. I am trying to convert PDF to Text. Link to the blog is here : (https://www.deepset.ai/blog/automating-information-extraction-with-question-answering) I pip installed…
Panda Bear
  • 11
  • 1
1
vote
1 answer

Unable to import transformers.models.bert.modeling_tf_bert on macOS?

As the title is self-descriptive, I'm not able to import the BertTokenizer and TFBertModel classes from the transformers package through the following code: from transformers import BertTokenizer, TFBertModel tokenizer =…
talha06
  • 6,206
  • 21
  • 92
  • 147
1
vote
1 answer

Unsupported/Invalid URL(s) when trying to add source to Language Studio knowledge base

I am trying to add a source from a Sharepoint page or Word document stored in Sharepoint using the URL-option I get the following error message: Unsupported/Invalid URL(s). It works just fine when adding a URL like this:…
DHjelm
  • 21
  • 5
1
vote
1 answer

AutoModelForQuestionAnswering: ValueError: too many values to unpack (expected 2)

When I initialized AutoModelForQuestionAnswering from pretrained indobenchmark/indobert-base-p1 it won’t produce any outputs and shows ValueError, below is the code: from transformers import AutoModelForQuestionAnswering, AutoTokenizer model =…
BlueRey
  • 35
  • 1
  • 6
1
vote
0 answers

generative question answering huggingface model

Is there an open-source generative question-answering model on huggingface where we can provide a large document as KB (Knowledge Base) such that given a question related to that KB, the model outputs a relevant answer?
user3303020
  • 933
  • 2
  • 12
  • 26
1
vote
1 answer

Given a subject and an object, what methods can i use to inference a possible verb?

Given a subject A and an object B, for example, A is "Peter", B is "iPhone", Peter can be 'playing' or 'using' iPhone, the verb varies depending on the context, in this case, what kinds of method can I use to inference a possible verb? I assume a…
YXlukarov
  • 36
  • 3
1
vote
0 answers

Getting error while doing Extractive Question Answering using the Haystack

I am trying to implement the Extractive QA using the ExtractiveQAPipeline from Haystack. I did the following steps: created the ElasticSearchDocuemntStore, then converted files to documents using convert_files_to_docs, written these documents to…
Swagat Mishra
  • 11
  • 1
1
vote
0 answers

Getting intermediate tensors for attention weight matrices in QnA mobilebert tf-js model without python/ajax

I have been using tfjs qna model, repo here for doing some question answering tasks. I wanted to access the internal model states for this model, specifically attention matrices for the intermediate layers that I want to display. My constraints are…
n404
  • 13
  • 2
1
vote
1 answer

An error in implementing regex function on a list

I was trying to implement a regex on a list of grammar tags in python, for finding the tense form of the list of grammar. And I wrote the following code to implement it. Data preprocessing: from nltk import word_tokenize, pos_tag import nltk text =…
Samar Pratap Singh
  • 471
  • 1
  • 10
  • 29
1
vote
2 answers

Extracting Questions and answers from any webpage's faq section using pytorch

I want to extract questions and answers from any webpage's FAQ section. An example: https://aws.amazon.com/ec2/autoscaling/faqs/ https://one.google.com/faq Currently I do this using regex parsing of html content of the page but thats very fragile,…
dasfdsa
  • 7,102
  • 8
  • 51
  • 93
1
vote
1 answer

How to use Huggingface Transformers with PrimeQA model?

Here is the model https://huggingface.co/PrimeQA/t5-base-table-question-generator Hugging face says that I should use the following code to use the model in transformers: from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer =…
Real Noob
  • 1,369
  • 2
  • 15
  • 29
1
vote
0 answers

How to link a storage blob or sharepoint as a knowlege base for question and answering of language studio?

I am using question and answering of language studio by uploading documents in their knowlegebase. I enabled Azure Search, so when I want to search documents and answers, I use the index created automatically by language studio. However, I want to…
userbin
  • 61
  • 9
1
vote
0 answers

How can I include the "source" field from the Microsoft Azure Custom Question Answer API?

I am leveraging the latest iteration of Azure's Custom question answering module in language studio in an external app that I've created, and I cannot figure out how to receive the actual source when the question is answered. I don't know if that's…
IMTheJuggernaut
  • 11
  • 3
1
vote
1 answer

QA model return the best answers to the same question from multiple contexts

I am trying to build a QA system using a pre-trained QA model. I have a list of texts and I basically want to extract the 'best x' answers to the same question using each text: example: contexts = ['the car is red', 'the car is yellow' , 'I love…
Carbo
  • 906
  • 5
  • 23
1
vote
0 answers

Unable to generate chunks (If length is greater than 512 in bert), we can use to split into chunks

I'm working Question & Answering hugging face pipeline, my sentence length is 3535, bert only takes 512 length, so i'm trying to divide into chunks and work on it. In the code, i'm working on question and answering model from hugging face, if the…
Mark
  • 331
  • 2
  • 10
1 2 3
…
16 17