Module rust_bert::pipelines::question_answering

Question Answering pipeline

Extractive question answering from a given question and context. By default, the dependencies for this model will be downloaded for a DistilBERT model finetuned on SQuAD (Stanford Question Answering Dataset). Customized DistilBERT models can be loaded by overwriting the resources in the configuration. The dependencies will be downloaded to the user's home directory, under ~/.cache/.rustbert/distilbert-qa

use rust_bert::pipelines::question_answering::{QuestionAnsweringModel, QaInput};

let qa_model = QuestionAnsweringModel::new(Default::default())?;

let question = String::from("Where does Amy live ?");
let context = String::from("Amy lives in Amsterdam");

let answers = qa_model.predict(&vec!(QaInput { question, context }), 1, 32);

Output:

[
    Answer {
        score: 0.9976,
        start: 13,
        end: 21,
        answer: "Amsterdam"
    }
]

Structs

Answer	Output for Question Answering
QaInput	Input for Question Answering
QuestionAnsweringConfig	Configuration for question answering
QuestionAnsweringModel	QuestionAnsweringModel to perform extractive question answering

Functions

squad_processor