6 votes
Accepted

Bert for QuestionAnswering input exceeds 512

The maximum input length is a limitation of the model by construction. That number defines the length of the positional embedding table, so you cannot provide a longer input, because it is not ...
user avatar
  • 16k
4 votes

Question answering (QA) vs Chatbots

Chatbots and Q&A systems differ in their complexity as well as use cases. Let's discuss each of them separately. Chatbots: They can answer various questions asked during an interactive ...
user avatar
3 votes

Question answering (QA) vs Chatbots

Question-answering (QA) is sometimes used to refer to the task where the input to the system is a question and a list of possible answers (normally only a handful) or a paragraph where the answer is ...
user avatar
  • 16k
3 votes
Accepted

learn information from text and resolve problem using transformers

Look at https://ai.facebook.com/blog/using-neural-networks-to-solve-advanced-mathematics-equations/ Treat to your problem like to MT task. Use transformer.
user avatar
2 votes
Accepted

Select best answer from several existing ones for a question

This problem is multiple choice answering question. I can see you have already tried gensim, doc2vec etc. You can try pytorch based transformer solution. Here is the link: multiple-choice . You can ...
user avatar
  • 106
1 vote

Model to implement Question Answering System over structured data

One efficient way is to use the roberta base squad 2 model, using your text as context and then ask questions. It should work well and the model can be downloaded directly. ...
user avatar
1 vote

Question answering bot: EM>F1, does it make sense?

Metrics for Q&A F1 score: Captures the precision and recall that words chosen as being part of the answer are actually part of the answer EM Score(exact match): which is the number of answers ...
user avatar
1 vote

Question answering bot: EM>F1, does it make sense?

EM (exact match) and F1 scores are typically calculated on different levels. EM is calculated on the character level. F1 is calculated on individual word level. Almost always, EM will be lower than F1....
user avatar
1 vote

Addressing polysemy in NLP tasks

Maybe this article will help you How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings. Talks about contextual word embeddings like BERT ...
user avatar
  • 610
1 vote
Accepted

which script can be used to finetune BERT fro squad question answering in hugging face library

A recent PR changed the location of the scripts you are looking for to examples/legacy/question-answering
user avatar
  • 16k
1 vote

Closed Domain Question Answering which doesn't answer Questions

Question Answering model of simpletransformers takes data with is_impossible option in the training phase. Also during ...
user avatar
1 vote

Answer to Question

Question answering (QA) is a complex problem and an active field of research. There are probably some academic prototypes around, but I doubt there's any general-purpose ready-to-use QA library. ...
user avatar
  • 22.1k
1 vote

Measuring quality of answers from QnA systems

The ranking of the answers is part of the ML process, i.e. a system should be trained to rank the answers according to their relevance. Heuristic measures such as the ones mentioned in your question ...
user avatar
  • 22.1k
1 vote

BERT - How Question answering is different than classification

For Question Answering, you need 2 logits : one for the start position, one for the end position. Based on these 2 logits, you have an answer span (denoted by the start/end position). In the source ...
user avatar
  • 859

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