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

Using BERT Q&A model (SQUAD) to answer questions from a dataset

I am developing a custom BERT Q&A model (in the same format as SQUAD) with a view to pose questions to a dataset for an answer (the dataset is large collection of reports). Is it possible to use the BERT model directly on the dataset, or would I…
Jon
  • 89
  • 6
0
votes
0 answers

PoS Tagging in QA Model

my code: import numpy as np def pos_tag_fun(x_list, tag): tagged_sentences = [] for sentence in x_list: tagged = nltk.pos_tag(sentence) tagged_sentences.append(tagged) print(tagged_sentences[0]) # Extract the sentences and the…
rash
  • 1
0
votes
0 answers

Prompt tuning for Dolly-v2-7b model for Question and Answer giving gibberish output?

I am following this page for Prompt tuning for Dolly-v2-7b model for Question and Answer: https://huggingface.co/docs/peft/task_guides/clm-prompt-tuning Instead of doing the training in old pytorch way. I am doing the training using Trainer api.…
MAC
  • 1,345
  • 2
  • 30
  • 60
0
votes
0 answers

can i use IndicBERT for question answering system

i want to build a question answering system in kannada language. the context is set for BMTC bus routes, the user asks a question "from kempegowda bus stand i want to go to Jallahalli cross, what are the buses i can take to get there?" answer "you…
Aniruddh H S
  • 23
  • 5
0
votes
1 answer

QnA model using Bert

I'm trying to build a bert model containing document as input. As bert's limitation is 512 tokens, it's unable to give accurate answer. Now, I'm trying to find NLP model/way/algorithm which should help bert model to find the correct answer. I tried…
Amrutha k
  • 39
  • 1
  • 4
0
votes
0 answers

Why Biobert has 499 Input tokens instead of 512?

Biobert input sequence length I am getting is 499 inspite of specifying it as 512 in tokenizer? How can this happen. Padding and truncation is set to TRUE. I am working on Squad dataset and for all the datapoints, I am getting input_ids length to be…
Shivang Shrivastav
  • 1
0
votes
0 answers

What is the key difference between graph-based QA and QA by semantic parsing?

Folowing D. Jurafsky handbook, i struggle with the chapter on QA. It defines 2 paradigms of QA knowledge based which are: graph-based QA (1) QA by semantic parsing (2) For (1) it takes the exemple: "When was Ada Lovelace born ?". The process is…
curious
  • 201
  • 1
  • 10
0
votes
0 answers

Python NLP error can anyone explain more to me of why this error is occuring due to inputs i assume but where am i wrong

This is my code I am able to execute all lines till the model. fit(X_train, y_train, epochs = 5, validation_data = (X_test, y_test)). I am just wondering if someone knows why and explain to me in detail I assume that my input variables in the line…
StevenIsReal
  • 1
  • 1
0
votes
1 answer

How to use tapas table question answer model when table size is big like containing 50000 rows?

I am trying to build up a model in which I load the dataframe (an excel file from Kaggle) and I am using TAPAS-large-finetuned-wtq model to query this dataset. I tried to query 259 rows (the memory usage is 62.9 KB). I didn't have a problem, but…
akshit bhatia
  • 573
  • 6
  • 22
0
votes
1 answer

Sentiment analysis feature extraction

I am new to NLP and feature extraction, i wish to create a machine learning model that can determine the sentiment of stock related social media posts. For feature extraction of my dataset I have opted to use Word2Vec. My question is: Is it…
user12383896
0
votes
1 answer

dataset to use for question formation from any text

I am trying to create an improved quiz generator that accepts a certain text as an input and forms questions from the sentences. I want to create a machine learning model that splits the sentence into different parts so it is capable of forming…
anonymous
  • 1
0
votes
0 answers

How to fix: AttributeError: 'spacy.tokens.span.Span' object has no attribute 'is_question'

This is the code I have written import spacy nlp = spacy.load("en_core_web_lg") passage="Natural language processing (NLP) refers to the branch of computer science—and more specifically, the branch of artificial intelligence or AI—concerned with…
JOSEPH BENNY
  • 1
0
votes
1 answer

Why do I get wrong number of keys in loglikelihood dictionary. Expected: 9165. Got: 9161

# Build the freqs dictionary for later uses freqs = count_tweets({}, train_x, train_y) # UNQ_C2 GRADED FUNCTION: train_naive_bayes def train_naive_bayes(freqs, train_x, train_y): ''' Input: freqs: dictionary from (word, label) to…
Electro01
  • 25
  • 2
  • 5
0
votes
0 answers

Question Answering training with using BERT

I'm developing a project by myself and I need help. I just created a dataset of questions and answers. Like this; Questions Answer Where is my laptop? On the work…
Onur Mesekalkan
  • 1
  • 1
0
votes
0 answers

Can not load exact model from Huggingface pipeline

I tried to load a model, which I found on HuggingFace: https://huggingface.co/deepset/gelectra-large-germanquad The pipeline shows different (but correct results) then loading the model. What do I need to do, to load the excat model from the…
Oweys
  • 47
  • 6
1 2 3
…
16 17