# Conversational Question Answering over Knowledge Graphs with Transformer and Graph Attention Networks

arXiv: https://arxiv.org/abs/2104.01569 · HTML: https://mlsanity.com/paper/2104.01569/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 27 references that are in the map.
- First posted on arXiv 4 Apr 2021.

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation](https://mlsanity.com/paper/1609.08144/) (2016)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [Key-Value Memory Networks for Directly Reading Documents](https://mlsanity.com/paper/1606.03126/) (2016)
- [Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models](https://mlsanity.com/paper/1507.04808/) (2015)
- [Variational Reasoning for Question Answering with Knowledge Graph](https://mlsanity.com/paper/1709.04071/) (2017)
- [Neural Approaches to Conversational AI](https://mlsanity.com/paper/1809.08267/) (2018)
- [Language to Logical Form with Neural Attention](https://mlsanity.com/paper/1601.01280/) (2016)
- [Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision](https://mlsanity.com/paper/1611.00020/) (2016)
- [Complex Sequential Question Answering: Towards Learning to Converse Over Linked Question Answer Pairs with a Knowledge Graph](https://mlsanity.com/paper/1801.10314/) (2018)
- [Look before you Hop: Conversational Question Answering over Knowledge Graphs Using Judicious Context Expansion](https://mlsanity.com/paper/1910.03262/) (2019)
- [Multi-Task Learning for Conversational Question Answering over a Large-Scale Knowledge Base](https://mlsanity.com/paper/1910.05069/) (2019)
- [Evaluating the Impact of Knowledge Graph Context on Entity Disambiguation Models](https://mlsanity.com/paper/2008.05190/) (2020)
- [MLM: A Benchmark Dataset for Multitask Learning with Multiple Languages and Modalities](https://mlsanity.com/paper/2008.06376/) (2020)

## Built on by (most cited first, 24 of 24)

- [Document Understanding Dataset and Evaluation (DUDE)](https://mlsanity.com/paper/2305.08455/) (2023)
- [KAG: Boosting LLMs in Professional Domains via Knowledge Augmented Generation](https://mlsanity.com/paper/2409.13731/) (2024)
- [Cross-modal Prototype Driven Network for Radiology Report Generation](https://mlsanity.com/paper/2207.04818/) (2022)
- [Complex Knowledge Base Question Answering: A Survey](https://mlsanity.com/paper/2108.06688/) (2021)
- [SPACE-3: Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generation](https://mlsanity.com/paper/2209.06664/) (2022)
- [Conversational Question Answering: A Survey](https://mlsanity.com/paper/2106.00874/) (2021)
- [SPACE-2: Tree-Structured Semi-Supervised Contrastive Pre-training for Task-Oriented Dialog Understanding](https://mlsanity.com/paper/2209.06638/) (2022)
- [Conversational Question Answering on Heterogeneous Sources](https://mlsanity.com/paper/2204.11677/) (2022)
- [Unifying Data Perspectivism and Personalization: An Application to Social Norms](https://mlsanity.com/paper/2210.14531/) (2022)
- [Structured Context and High-Coverage Grammar for Conversational Question Answering over Knowledge Graphs](https://mlsanity.com/paper/2109.00269/) (2021)
- [Semantic Parsing for Conversational Question Answering over Knowledge Graphs](https://mlsanity.com/paper/2301.12217/) (2023)
- [Robust Training for Conversational Question Answering Models with Reinforced Reformulation Generation](https://mlsanity.com/paper/2310.13505/) (2023)
- [Evaluating Large Language Models in Semantic Parsing for Conversational Question Answering over Knowledge Graphs](https://mlsanity.com/paper/2401.01711/) (2024)
- [GETT-QA: Graph Embedding based T2T Transformer for Knowledge Graph Question Answering](https://mlsanity.com/paper/2303.13284/) (2023)
- [GraphWOZ: Dialogue Management with Conversational Knowledge Graphs](https://mlsanity.com/paper/2211.12852/) (2022)
- [History Semantic Graph Enhanced Conversational KBQA with Temporal Information Modeling](https://mlsanity.com/paper/2306.06872/) (2023)
- [Learning to Select the Relevant History Turns in Conversational Question Answering](https://mlsanity.com/paper/2308.02294/) (2023)
- [VOGUE: Answer Verbalization through Multi-Task Learning](https://mlsanity.com/paper/2106.13316/) (2021)
- [UniPCM: Universal Pre-trained Conversation Model with Task-aware Automatic Prompt](https://mlsanity.com/paper/2309.11065/) (2023)
- [Contrastive Representation Learning for Conversational Question Answering over Knowledge Graphs](https://mlsanity.com/paper/2210.04373/) (2022)
- [Conversational Semantic Parsing using Dynamic Context Graphs](https://mlsanity.com/paper/2305.06164/) (2023)
- [An Answer Verbalization Dataset for Conversational Question Answerings over Knowledge Graphs](https://mlsanity.com/paper/2208.06734/) (2022)
- [A Survey of the State-of-the-Art in Conversational Question Answering Systems](https://mlsanity.com/paper/2509.05716/) (2025)
- [Learning Section Weights for Multi-Label Document Classification](https://mlsanity.com/paper/2311.15402/) (2023)

## Abstract (arXiv)

This paper addresses the task of (complex) conversational question answering over a knowledge graph. For this task, we propose LASAGNE (muLti-task semAntic parSing with trAnsformer and Graph atteNtion nEtworks). It is the first approach, which employs a transformer architecture extended with Graph Attention Networks for multi-task neural semantic parsing. LASAGNE uses a transformer model for generating the base logical forms, while the Graph Attention model is used to exploit correlations between (entity) types and predicates to produce node representations. LASAGNE also includes a novel entity recognition module which detects, links, and ranks all relevant entities in the question context. We evaluate LASAGNE on a standard dataset for complex sequential question answering, on which it outperforms existing baseline averages on all question types. Specifically, we show that LASAGNE improves the F1-score on eight out of ten question types; in some cases, the increase in F1-score is more than 20% compared to the state of the art.