“What makes a question inquisitive?” A Study on Type-Controlled Inquisitive Question Generation

@article{Gao2022WhatMA,
  title={“What makes a question inquisitive?” A Study on Type-Controlled Inquisitive Question Generation},
  author={Lingyu Gao and Debanjan Ghosh and Kevin Gimpel},
  journal={ArXiv},
  year={2022},
  volume={abs/2205.08056}
}
We propose a type-controlled framework for inquisitive question generation. We annotate an inquisitive question dataset with question types, train question type classifiers, and finetune models for type-controlled question generation. Empirical results demonstrate that we can generate a variety of questions that adhere to specific types while drawing from the source texts. We also investigate strategies for selecting a single question from a generated set, considering both an informative vs… 

References

SHOWING 1-10 OF 62 REFERENCES
Inquisitive Question Generation for High Level Text Comprehension
TLDR
This work introduces INQUISITIVE, a dataset of ~19K questions that are elicited while a person is reading through a document, and shows that readers engage in a series of pragmatic strategies to seek information.
Language Models are Unsupervised Multitask Learners
TLDR
It is demonstrated that language models begin to learn these tasks without any explicit supervision when trained on a new dataset of millions of webpages called WebText, suggesting a promising path towards building language processing systems which learn to perform tasks from their naturally occurring demonstrations.
Bleu: a Method for Automatic Evaluation of Machine Translation
TLDR
This work proposes a method of automatic machine translation evaluation that is quick, inexpensive, and language-independent, that correlates highly with human evaluation, and that has little marginal cost per run.
BERTScore: Evaluating Text Generation with BERT
TLDR
This work proposes BERTScore, an automatic evaluation metric for text generation that correlates better with human judgments and provides stronger model selection performance than existing metrics.
SQuAD: 100,000+ Questions for Machine Comprehension of Text
TLDR
A strong logistic regression model is built, which achieves an F1 score of 51.0%, a significant improvement over a simple baseline (20%).
Meteor Universal: Language Specific Translation Evaluation for Any Target Language
TLDR
Meteor Universal brings language specific evaluation to previously unsupported target languages by automatically extracting linguistic resources from the bitext used to train MT systems and using a universal parameter set learned from pooling human judgments of translation quality from several language directions.
Building a Large Annotated Corpus of English: The Penn Treebank
TLDR
As a result of this grant, the researchers have now published on CDROM a corpus of over 4 million words of running text annotated with part-of- speech (POS) tags, which includes a fully hand-parsed version of the classic Brown corpus.
Controllable Open-ended Question Generation with A New Question Type Ontology
TLDR
This work proposes a novel question type-aware question generation framework, augmented by a semantic graph representation, to jointly predict question focuses and produce the question and uses both exemplars and automatically generated templates to improve controllability and diversity.
On the Importance of Diversity in Question Generation for QA
TLDR
It is shown that diversity-promoting QG indeed provides better QA training than likelihood maximization approaches such as beam search, and a diversity-aware intrinsic measure of overall QG quality that correlates well with extrinsic evaluation on QA is proposed.
BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
TLDR
BART is presented, a denoising autoencoder for pretraining sequence-to-sequence models, which matches the performance of RoBERTa on GLUE and SQuAD, and achieves new state-of-the-art results on a range of abstractive dialogue, question answering, and summarization tasks.
...
...