About

The goal of Question Generation is to generate a valid and fluent question according to a given passage and the target answer. Question Generation can be used in many scenarios, such as automatic tutoring systems, improving the performance of Question Answering models and enabling chatbots to lead a conversation.

Source: Generating Highly Relevant Questions

Benchmarks

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Datasets

Greatest papers with code

ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training

13 Jan 2020huggingface/transformers

This paper presents a new sequence-to-sequence pre-training model called ProphetNet, which introduces a novel self-supervised objective named future n-gram prediction and the proposed n-stream self-attention mechanism.

Ranked #3 on Abstractive Text Summarization on CNN / Daily Mail (using extra training data)

ABSTRACTIVE TEXT SUMMARIZATION QUESTION GENERATION

Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models

7 Oct 2016facebookresearch/fairseq-py

We observe that our method consistently outperforms BS and previously proposed techniques for diverse decoding from neural sequence models.

IMAGE CAPTIONING MACHINE TRANSLATION QUESTION GENERATION TEXT GENERATION TIME SERIES

ERNIE-GEN: An Enhanced Multi-Flow Pre-training and Fine-tuning Framework for Natural Language Generation

26 Jan 2020PaddlePaddle/ERNIE

Current pre-training works in natural language generation pay little attention to the problem of exposure bias on downstream tasks.

 Ranked #1 on Text Summarization on GigaWord-10k (using extra training data)

ABSTRACTIVE TEXT SUMMARIZATION DIALOGUE GENERATION GENERATIVE QUESTION ANSWERING QUESTION GENERATION

Synthetic Data Augmentation for Zero-Shot Cross-Lingual Question Answering

23 Oct 2020microsoft/unilm

Coupled with the availability of large scale datasets, deep learning architectures have enabled rapid progress on the Question Answering task.

CROSS-LINGUAL QUESTION ANSWERING DATA AUGMENTATION QUESTION ANSWERING QUESTION GENERATION

UniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Training

28 Feb 2020microsoft/unilm

We propose to pre-train a unified language model for both autoencoding and partially autoregressive language modeling tasks using a novel training procedure, referred to as a pseudo-masked language model (PMLM).

Ranked #3 on Question Generation on SQuAD1.1 (using extra training data)

ABSTRACTIVE TEXT SUMMARIZATION LANGUAGE MODELLING NATURAL LANGUAGE UNDERSTANDING QUESTION GENERATION

Transformer-based End-to-End Question Generation

3 May 2020patil-suraj/question_generation

Question generation (QG) is a natural language generation task where a model is trained to ask questions corresponding to some input text.

LANGUAGE MODELLING QUESTION GENERATION TEXT GENERATION TRANSFER LEARNING

Synthetic QA Corpora Generation with Roundtrip Consistency

ACL 2019 patil-suraj/question_generation

We introduce a novel method of generating synthetic question answering corpora by combining models of question generation and answer extraction, and by filtering the results to ensure roundtrip consistency.

QUESTION ANSWERING QUESTION GENERATION SYNTHETIC DATA GENERATION

Learning to Ask: Neural Question Generation for Reading Comprehension

ACL 2017 xinyadu/nqg

We study automatic question generation for sentences from text passages in reading comprehension.

QUESTION GENERATION READING COMPREHENSION

ProphetNet-X: Large-Scale Pre-training Models for English, Chinese, Multi-lingual, Dialog, and Code Generation

16 Apr 2021microsoft/ProphetNet

ProphetNet is a pre-training based natural language generation method which shows powerful performance on English text summarization and question generation tasks.

CODE GENERATION OPEN-DOMAIN DIALOG QUESTION GENERATION TEXT GENERATION TEXT SUMMARIZATION