# Conversational Question Answering with Reformulations over Knowledge Graph

arXiv: https://arxiv.org/abs/2312.17269 · HTML: https://mlsanity.com/paper/2312.17269/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 32 references that are in the map.
- First posted on arXiv 27 Dec 2023.

## Builds on (most cited first, 17 of 17)

- [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)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Complex Embeddings for Simple Link Prediction](https://mlsanity.com/paper/1606.06357/) (2016)
- [DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning](https://mlsanity.com/paper/1707.06690/) (2017)
- [The Design and Implementation of XiaoIce, an Empathetic Social Chatbot](https://mlsanity.com/paper/1812.08989/) (2018)
- [Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning](https://mlsanity.com/paper/1711.05851/) (2017)
- [Multi-Hop Knowledge Graph Reasoning with Reward Shaping](https://mlsanity.com/paper/1808.10568/) (2018)
- [Question Rewriting for Conversational Question Answering](https://mlsanity.com/paper/2004.14652/) (2020)
- [Ask the Right Questions: Active Question Reformulation with Reinforcement Learning](https://mlsanity.com/paper/1705.07830/) (2017)
- [Task-Oriented Query Reformulation with Reinforcement Learning](https://mlsanity.com/paper/1704.04572/) (2017)
- [Towards End-to-End Reinforcement Learning of Dialogue Agents for Information Access](https://mlsanity.com/paper/1609.00777/) (2016)
- [Benchmarking the Combinatorial Generalizability of Complex Query Answering on Knowledge Graphs](https://mlsanity.com/paper/2109.08925/) (2021)
- [Reinforcement Learning from Reformulations in Conversational Question Answering over Knowledge Graphs](https://mlsanity.com/paper/2105.04850/) (2021)
- [Alexa Conversations: An Extensible Data-driven Approach for Building Task-oriented Dialogue Systems](https://mlsanity.com/paper/2104.09088/) (2021)
- [Structured Context and High-Coverage Grammar for Conversational Question Answering over Knowledge Graphs](https://mlsanity.com/paper/2109.00269/) (2021)

## Built on by (most cited first, 4 of 4)

- [Neural Active Learning Beyond Bandits](https://mlsanity.com/paper/2404.12522/) (2024)
- [Can Contrastive Learning Refine Embeddings](https://mlsanity.com/paper/2404.08701/) (2024)
- [Reinforcement Learning for Conversational Question Answering over Knowledge Graph](https://mlsanity.com/paper/2401.08460/) (2024)
- [Advanced Academic Team Worker Recommendation Models](https://mlsanity.com/paper/2402.16876/) (2024)

## Abstract (arXiv)

Conversational question answering (convQA) over knowledge graphs (KGs) involves answering multi-turn natural language questions about information contained in a KG. State-of-the-art methods of ConvQA often struggle with inexplicit question-answer pairs. These inputs are easy for human beings to understand given a conversation history, but hard for a machine to interpret, which can degrade ConvQA performance. To address this problem, we propose a reinforcement learning (RL) based model, CornNet, which utilizes question reformulations generated by large language models (LLMs) to improve ConvQA performance. CornNet adopts a teacher-student architecture where a teacher model learns question representations using human writing reformulations, and a student model to mimic the teacher model's output via reformulations generated by LLMs. The learned question representation is then used by an RL model to locate the correct answer in a KG. Extensive experimental results show that CornNet outperforms state-of-the-art convQA models.