# Learning to Ask Questions in Open-domain Conversational Systems with Typed Decoders

arXiv: https://arxiv.org/abs/1805.04843 · HTML: https://mlsanity.com/paper/1805.04843/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 May 2018.

## Built on by (most cited first, 26 of 26)

- [HalluLens: LLM Hallucination Benchmark](https://mlsanity.com/paper/2504.17550/) (2025)
- [Building and Evaluating Open-Domain Dialogue Corpora with Clarifying Questions](https://mlsanity.com/paper/2109.05794/) (2021)
- [ArchivalQA: A Large-scale Benchmark Dataset for Open Domain Question Answering over Historical News Collections](https://mlsanity.com/paper/2109.03438/) (2021)
- [DialogueNeRF: Towards Realistic Avatar Face-to-Face Conversation Video Generation](https://mlsanity.com/paper/2203.07931/) (2022)
- [MixQG: Neural Question Generation with Mixed Answer Types](https://mlsanity.com/paper/2110.08175/) (2021)
- [Evaluating Mixed-initiative Conversational Search Systems via User Simulation](https://mlsanity.com/paper/2204.08046/) (2022)
- [From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?](https://mlsanity.com/paper/2506.08295/) (2025)
- [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)
- [What should I Ask: A Knowledge-driven Approach for Follow-up Questions Generation in Conversational Surveys](https://mlsanity.com/paper/2205.10977/) (2022)
- [Diverse and Specific Clarification Question Generation with Keywords](https://mlsanity.com/paper/2104.10317/) (2021)
- [Generating Usage-related Questions for Preference Elicitation in Conversational Recommender Systems](https://mlsanity.com/paper/2111.13463/) (2021)
- [QRelScore: Better Evaluating Generated Questions with Deeper Understanding of Context-aware Relevance](https://mlsanity.com/paper/2204.13921/) (2022)
- [Evaluation of Question Generation Needs More References](https://mlsanity.com/paper/2305.16626/) (2023)
- [Modeling What-to-ask and How-to-ask for Answer-unaware Conversational Question Generation](https://mlsanity.com/paper/2305.03088/) (2023)
- [Inductive-Deductive Strategy Reuse for Multi-Turn Instructional Dialogues](https://mlsanity.com/paper/2404.11095/) (2024)
- [Controllable Dialogue Generation with Disentangled Multi-grained Style Specification and Attribute Consistency Reward](https://mlsanity.com/paper/2109.06717/) (2021)
- [Conversational QA Dataset Generation with Answer Revision](https://mlsanity.com/paper/2209.11396/) (2022)
- [Towards Efficient Dialogue Pre-training with Transferable and Interpretable Latent Structure](https://mlsanity.com/paper/2210.12461/) (2022)
- [Collaborative Reasoning on Multi-Modal Semantic Graphs for Video-Grounded Dialogue Generation](https://mlsanity.com/paper/2210.12460/) (2022)
- [Learning to Express in Knowledge-Grounded Conversation](https://mlsanity.com/paper/2204.05805/) (2022)
- [From Superficial to Deep: Integrating External Knowledge for Follow-up Question Generation Using Knowledge Graph and LLM](https://mlsanity.com/paper/2504.05801/) (2025)
- [On the Evaluation of Answer-Agnostic Paragraph-level Multi-Question Generation](https://mlsanity.com/paper/2203.04464/) (2022)
- [Let's Talk! Striking Up Conversations via Conversational Visual Question Generation](https://mlsanity.com/paper/2205.09327/) (2022)
- [Learning to Detect Relevant Contexts and Knowledge for Response Selection in Retrieval-based Dialogue Systems](https://mlsanity.com/paper/2509.22845/) (2025)
- [Clarification Is Not Enough: Post-Clarification Answering Remains the Bottleneck in Multi-Turn QA](https://mlsanity.com/paper/2605.25204/) (2026)

## Abstract (arXiv)

Asking good questions in large-scale, open-domain conversational systems is quite significant yet rather untouched. This task, substantially different from traditional question generation, requires to question not only with various patterns but also on diverse and relevant topics. We observe that a good question is a natural composition of it interrogatives, it topic words, and it ordinary words. Interrogatives lexicalize the pattern of questioning, topic words address the key information for topic transition in dialogue, and ordinary words play syntactical and grammatical roles in making a natural sentence. We devise two typed decoders (textitsoft typed decoder and textithard typed decoder) in which a type distribution over the three types is estimated and used to modulate the final generation distribution. Extensive experiments show that the typed decoders outperform state-of-the-art baselines and can generate more meaningful questions.