OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Models

Question Generation

Question Generation is a Python seq2seq model that takes text and an answer as input and produces questions. Its documented command-line workflow returns TSV containing a question, answer and score, using an environment set up with OpenNMT and CoreNLP servers.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Question Generation — OpenViST project profile in AI Models.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you can run its documented Python and Docker-based setup locally and need question-and-answer records from text in TSV format.

Who it is for

  • Educators or content developers preparing candidate questions from source passages.
  • Dataset preparers creating question-answer pairs from selected text.
  • Developers adding question generation to a command-line text-processing workflow.

Documented uses

  • Generate candidate questions from a passage and a supplied answer.
  • Produce TSV rows containing questions, answers and scores for downstream text processing.
Before you choose

Requirements & limits

The project is a public repository identified as GPL-3.0 licensed. The documented workflow runs through local setup and command-line scripts.

  • The setup script downloads the model and starts OpenNMT and CoreNLP servers, so use requires the documented Docker, Docker Compose, Python and pyzmq prerequisites.
  • The first model feed may be slow because CoreNLP modules load.
  • Output includes a score, but the README gives no interpretation or selection guidance for it.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up the question-generation workflow and request TSV output

Install the documented components and use the command-line script to generate TSV from a text passage.

Before you start

  • Docker 17.03 or later
  • Docker Compose 1.13.0 or later
  • Python 3
  • pyzmq dependencies; the README lists libzmq3-dev for Ubuntu and zeromq with libpgm for Mac

Steps

  1. Install the listed environment requirements for your platform.

  2. Run ./setup to download the model, install Python requirements, pull Docker images and start the OpenNMT and CoreNLP servers.

  3. Run ./get_qnas "" with a passage as the input.

Expected outcome

The script returns TSV with a question, answer and score in each row.

Guide limitations

  • The first model feed may take a long time while CoreNLP modules load.
  • The README does not define how to interpret or filter the output score.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
deeppavlov/question_generation · Official homepage title · retained in its source language
How we review sourcesSuggest a correction