# Modeling What-to-ask and How-to-ask for Answer-unaware Conversational Question Generation

arXiv: https://arxiv.org/abs/2305.03088 · HTML: https://mlsanity.com/paper/2305.03088/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 57 references that are in the map.
- First posted on arXiv 4 May 2023.

## Builds on (most cited first, 29 of 29)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [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)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [fairseq: A Fast, Extensible Toolkit for Sequence Modeling](https://mlsanity.com/paper/1904.01038/) (2019)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [CoQA: A Conversational Question Answering Challenge](https://mlsanity.com/paper/1808.07042/) (2018)
- [Towards a Human-like Open-Domain Chatbot](https://mlsanity.com/paper/2001.09977/) (2020)
- [A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Stories](https://mlsanity.com/paper/1604.01696/) (2016)
- [Simple BERT Models for Relation Extraction and Semantic Role Labeling](https://mlsanity.com/paper/1904.05255/) (2019)
- [Synthetic QA Corpora Generation with Roundtrip Consistency](https://mlsanity.com/paper/1906.05416/) (2019)
- [Training Question Answering Models From Synthetic Data](https://mlsanity.com/paper/2002.09599/) (2020)
- [A Comprehensive Assessment of Dialog Evaluation Metrics](https://mlsanity.com/paper/2106.03706/) (2021)
- [End-to-End Synthetic Data Generation for Domain Adaptation of Question Answering Systems](https://mlsanity.com/paper/2010.06028/) (2020)
- [Towards Exploiting Background Knowledge for Building Conversation Systems](https://mlsanity.com/paper/1809.08205/) (2018)
- [Evaluating Coherence in Dialogue Systems using Entailment](https://mlsanity.com/paper/1904.03371/) (2019)
- [Better Automatic Evaluation of Open-Domain Dialogue Systems with Contextualized Embeddings](https://mlsanity.com/paper/1904.10635/) (2019)
- [Recent Advances in Neural Question Generation](https://mlsanity.com/paper/1905.08949/) (2019)
- [Learning to Ask Questions in Open-domain Conversational Systems with Typed Decoders](https://mlsanity.com/paper/1805.04843/) (2018)
- [Interconnected Question Generation with Coreference Alignment and Conversation Flow Modeling](https://mlsanity.com/paper/1906.06893/) (2019)
- [Stay Hungry, Stay Focused: Generating Informative and Specific Questions in Information-Seeking Conversations](https://mlsanity.com/paper/2004.14530/) (2020)
- [ChainCQG: Flow-Aware Conversational Question Generation](https://mlsanity.com/paper/2102.02864/) (2021)
- [GTM: A Generative Triple-Wise Model for Conversational Question Generation](https://mlsanity.com/paper/2106.03635/) (2021)
- [Reinforced Dynamic Reasoning for Conversational Question Generation](https://mlsanity.com/paper/1907.12667/) (2019)
- [Synthetic Question Value Estimation for Domain Adaptation of Question Answering](https://mlsanity.com/paper/2203.08926/) (2022)
- [CoHS-CQG: Context and History Selection for Conversational Question Generation](https://mlsanity.com/paper/2209.06652/) (2022)

## Built on by (most cited first, 6 of 6)

- [Book2Dial: Generating Teacher-Student Interactions from Textbooks for Cost-Effective Development of Educational Chatbots](https://mlsanity.com/paper/2403.03307/) (2024)
- [MinPrompt: Graph-based Minimal Prompt Data Augmentation for Few-shot Question Answering](https://mlsanity.com/paper/2310.05007/) (2023)
- [Incubating Text Classifiers Following User Instruction with Nothing but LLM](https://mlsanity.com/paper/2404.10877/) (2024)
- [A Survey on Neural Question Generation: Methods, Applications, and Prospects](https://mlsanity.com/paper/2402.18267/) (2024)
- [Self-Supervised Position Debiasing for Large Language Models](https://mlsanity.com/paper/2401.01218/) (2024)
- [An Answer is just the Start: Related Insight Generation for Open-Ended Document-Grounded QA](https://mlsanity.com/paper/2604.19685/) (2026)

## Abstract (arXiv)

Conversational Question Generation (CQG) is a critical task for machines to assist humans in fulfilling their information needs through conversations. The task is generally cast into two different settings: answer-aware and answer-unaware. While the former facilitates the models by exposing the expected answer, the latter is more realistic and receiving growing attentions recently. What-to-ask and how-to-ask are the two main challenges in the answer-unaware setting. To address the first challenge, existing methods mainly select sequential sentences in context as the rationales. We argue that the conversation generated using such naive heuristics may not be natural enough as in reality, the interlocutors often talk about the relevant contents that are not necessarily sequential in context. Additionally, previous methods decide the type of question to be generated (boolean/span-based) implicitly. Modeling the question type explicitly is crucial as the answer, which hints the models to generate a boolean or span-based question, is unavailable. To this end, we present SG-CQG, a two-stage CQG framework. For the what-to-ask stage, a sentence is selected as the rationale from a semantic graph that we construct, and extract the answer span from it. For the how-to-ask stage, a classifier determines the target answer type of the question via two explicit control signals before generating and filtering. In addition, we propose Conv-Distinct, a novel evaluation metric for CQG, to evaluate the diversity of the generated conversation from a context. Compared with the existing answer-unaware CQG models, the proposed SG-CQG achieves state-of-the-art performance.