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
1 answer

How to convert a list of words into multiple sentences in python

Eg: Input: Name: ['FirstName','LastName','FirstNameLastName'] Customer Account Number: ['Customer', 'Account', 'Number', 'Customer Account', 'Customer Number', 'Customer Account Number'] output: FirstNameLastName Customer Account Number
Subash S
  • 1
0
votes
0 answers

How do I convert a huggingface-transformers deepset/roberta-base-squad2 model for question answering to TensorRT engine and run Inference on it?

I want to convert HuggingFace-Transformers deepset/roberta-base-squad2 model for question answering into TensorRT to boost inference speed and performance of the engine. Since the model uses pytorch framework, I converted the model into ONNX format…
Naman Jain
  • 1
  • 1
0
votes
0 answers

Generating multiple samples using hugging face QuestionAnsweringPipeline not accept List of strings

I am trying to use a hugging face QA model with Squad2_es. class QAInferencer: def __init__(self, model, tokenizer): self.pipeline: QuestionAnsweringPipeline = pipeline( model=model, tokenizer=(tokenizer,…
Nasgar
  • 859
  • 2
  • 11
  • 26
0
votes
0 answers

How to deal with -1 span_start and span_end in CoQA dataset? Posted in Questions & Answers a minute ago

I am trying to fine tune the coQA dataset on 'bert-base-uncased' from hugging face. I am getting error while adding token positions. Upon checking I got some of the 'span_start' and 'span_end' in the 'answers' in training set as -1 which is throwing…
Nancy
  • 55
  • 2
  • 13
0
votes
1 answer

Some keys are not used by the HfArgumentParser

raise ValueError(f"Some keys are not used by the HfArgumentParser: {sorted(unused_keys)}") ValueError: Some keys are not used by the HfArgumentParser: ['max_len', 'model_name_or_path', 'use_cache'] The same code runs successfully in local…
Stephen L
  • 1
  • 1
0
votes
0 answers

Is it possible to train a question answering model that have multiple correct answers?

I'm trying to create a question answering model follow the guide provided by Huggingface. But in the training data for each question and context pair there is only one correct answer and its start_index. So what if the context contains more than one…
Long Phi Do Hai
  • 1
0
votes
0 answers

How to mock GetAnswersAsync function in Custom question answering service

I have migrated from QNA maker to Custom question answering service for the bot project. Now, I want to mock the function , Task GetAnswersAsync(int qnaId, QuestionAnsweringProject project, AnswersOptions options = null, CancellationToken…
Aiswarya
  • 21
  • 4
0
votes
0 answers

Is it possible to run KBQA method on self-constructed graphs?

It's common that a KBQA method can run on some big databases such as wikidata or FreeBase, but what if run this on a self-constructed graph that only contain informations from a certain field? For example, input the graph(a subgraph of wikidata, or…
Walter
  • 21
  • 1
0
votes
0 answers

Next sentence prediction / question answering WITHOUT token_type_ids?

Apparently, BERT tokenizer returns input_ids, attention_mask and token_type_ids, where token_type_ids are used if we have NSP or QA task (it is used to differentiate between the Context and the aspect (question, next sentence, and so on)). In my…
Petar Ulev
  • 311
  • 4
  • 12
0
votes
0 answers

Execute huggingface QA Model in parallel

I am trying to build a QA model which gets a question from front end and pass it backs the answers. The latency time is 95 seconds right now which is very high for the online application. Internally, my backend code fetches a maximum of 100 contexts…
usr_lal123
  • 650
  • 12
  • 28
0
votes
1 answer

I want to make cluster of sentences but now i don't know that how many cluster will be made

I have calculated the embedding with the help of doc2vec and I have also calculated the distance between sentences in vector form. now I have a vector of sentences that tells the distance between them(sentences). how can I cluster them without…
rahul verma
  • 1
  • 2
0
votes
0 answers

QnA Maker Migration to Azure Custom Question Answering

I migrated existing QnA Maker knowledge base to Custom Question Answering(in Azure). I created chat bot in teams. The bot responses in teams are displayed as raw Markdown text instead of displaying it in markdown style. e.g. Testing , is displayed…
Arock Durai
  • 13
  • 3
0
votes
1 answer

Is there an API for the Azure Language Studio, especially for Custom Question Answering?

i am currently working with the Language Studio by Azure. For now, i am wondering if there is an API for this, especially for the Custom Question Answering that i can work with on my current project.
deetwo-id
  • 245
  • 1
  • 10
0
votes
1 answer

How to enlarge Custom Question Answering Editor Window in Language Studio

The existing QnA maker editor will be always better than the current custom question answering in the azure language studio. We have added 600+ QnA question pairs in custom question answering but the editor is very small and we can able to see only…
Rajeesh Menoth
  • 1,704
  • 3
  • 17
  • 33
0
votes
0 answers

how to train and test a deep learning model on github with my dataset?

I am trying to train and test the VQA model on https://github.com/akirafukui/vqa-mcb with my own dataset. I learned a deeplearning unit at Uni, but I still don't know how to make use of the model in my code. Also, I don't understand the…
Lucy Cai
  • 1
  • 1
1 2 3
…
16 17