# Semantic-Based Self-Critical Training For Question Generation

arXiv: https://arxiv.org/abs/2108.12026 · HTML: https://mlsanity.com/paper/2108.12026/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 25 references that are in the map.
- First posted on arXiv 26 Aug 2021.

## Builds on (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Self-critical Sequence Training for Image Captioning](https://mlsanity.com/paper/1612.00563/) (2016)
- [Are Transformers universal approximators of sequence-to-sequence functions?](https://mlsanity.com/paper/1912.10077/) (2019)
- [ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training](https://mlsanity.com/paper/2001.04063/) (2020)
- [PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them](https://mlsanity.com/paper/2102.07033/) (2021)
- [Neural Question Generation from Text: A Preliminary Study](https://mlsanity.com/paper/1704.01792/) (2017)
- [Reinforcement Learning Based Graph-to-Sequence Model for Natural Question Generation](https://mlsanity.com/paper/1908.04942/) (2019)
- [A Graph-to-Sequence Model for AMR-to-Text Generation](https://mlsanity.com/paper/1805.02473/) (2018)
- [Answer-based Adversarial Training for Generating Clarification Questions](https://mlsanity.com/paper/1904.02281/) (2019)
- [NUBIA: NeUral Based Interchangeability Assessor for Text Generation](https://mlsanity.com/paper/2004.14667/) (2020)
- [Learning to Generate Questions by Learning What not to Generate](https://mlsanity.com/paper/1902.10418/) (2019)
- [Sequential Copying Networks](https://mlsanity.com/paper/1807.02301/) (2018)
- [Question Generation by Transformers](https://mlsanity.com/paper/1909.05017/) (2019)

## Abstract (arXiv)

Question generation is a conditioned language generation task that consists in generating a context-aware question given a context and the targeted answer. Train language modelling with a mere likelihood maximization has been widely used while suffering from exposure bias and the discordance between the training and the test metrics. In the way of addressing this issue, The presented work portrays a fully Transformer-based reinforcement learning generator-evaluation architecture for neural question generation. To edge the flexibility of the generation, a semantic-based reward score was externally infused during the training to drive the training of the language model. The global architecture is laid out in a generator-evaluator fashion optimized directly to n-gram and semantic-based metrics. Evaluation metrics for language modelling only based on n-gram overlapping do not consider semantic relations between reference and candidate sequences. To improve the evaluation step, a two-fold evaluation was carried out. On the one side, an n-gram overlapping evaluation using the BLEU score. On the other side, a semantic-based assessment using BERTScore and NUBIA. The results were corroborated by a binary human evaluation of the semantic relatedness of the generated question and the ground truth. The results obtained showed that use a semantic-based REINFORCE algorithm for the question generation syntactically reshapes the generated questions while preserving their underlying semantic meaning. Many downstream applications can be drawn from a successful question generation including the enlargement of question answering datasets, the improvement of conversational systems, the enhancement of autonomous educational assessment systems, and so forth.