# Structured Context and High-Coverage Grammar for Conversational Question Answering over Knowledge Graphs

arXiv: https://arxiv.org/abs/2109.00269 · HTML: https://mlsanity.com/paper/2109.00269/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 49 references that are in the map.
- First posted on arXiv 1 Sep 2021.

## Builds on (most cited first, 30 of 33)

- [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)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [Carbon Emissions and Large Neural Network Training](https://mlsanity.com/paper/2104.10350/) (2021)
- [TAPAS: Weakly Supervised Table Parsing via Pre-training](https://mlsanity.com/paper/2004.02349/) (2020)
- [Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks](https://mlsanity.com/paper/1503.00075/) (2015)
- [Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation](https://mlsanity.com/paper/1905.08205/) (2019)
- [Graph-Bert: Only Attention is Needed for Learning Graph Representations](https://mlsanity.com/paper/2001.05140/) (2020)
- [Language to Logical Form with Neural Attention](https://mlsanity.com/paper/1601.01280/) (2016)
- [Data Recombination for Neural Semantic Parsing](https://mlsanity.com/paper/1606.03622/) (2016)
- [Coarse-to-Fine Decoding for Neural Semantic Parsing](https://mlsanity.com/paper/1805.04793/) (2018)
- [Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision](https://mlsanity.com/paper/1611.00020/) (2016)
- [Tree-to-tree Neural Networks for Program Translation](https://mlsanity.com/paper/1802.03691/) (2018)
- [A Comprehensive Exploration on WikiSQL with Table-Aware Word Contextualization](https://mlsanity.com/paper/1902.01069/) (2019)
- [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)
- [Graph-to-Tree Neural Networks for Learning Structured Input-Output Translation with Applications to Semantic Parsing and Math Word Problem](https://mlsanity.com/paper/2004.13781/) (2020)
- [Message Passing for Complex Question Answering over Knowledge Graphs](https://mlsanity.com/paper/1908.06917/) (2019)
- [Conversational Question Answering over Knowledge Graphs with Transformer and Graph Attention Networks](https://mlsanity.com/paper/2104.01569/) (2021)
- [Tree-Transformer: A Transformer-Based Method for Correction of Tree-Structured Data](https://mlsanity.com/paper/1908.00449/) (2019)
- [Unsupervised Dual Paraphrasing for Two-stage Semantic Parsing](https://mlsanity.com/paper/2005.13485/) (2020)
- [Coupling Retrieval and Meta-Learning for Context-Dependent Semantic Parsing](https://mlsanity.com/paper/1906.07108/) (2019)
- [Generating Logical Forms from Graph Representations of Text and Entities](https://mlsanity.com/paper/1905.08407/) (2019)
- [Context Transformer with Stacked Pointer Networks for Conversational Question Answering over Knowledge Graphs](https://mlsanity.com/paper/2103.07766/) (2021)
- [Exploiting Rich Syntactic Information for Semantic Parsing with Graph-to-Sequence Model](https://mlsanity.com/paper/1808.07624/) (2018)
- [Improving Tree-LSTM with Tree Attention](https://mlsanity.com/paper/1901.00066/) (2019)
- [Template-based Question Answering using Recursive Neural Networks](https://mlsanity.com/paper/2004.13843/) (2020)

## Built on by (most cited first, 10 of 10)

- [Conversational Question Answering on Heterogeneous Sources](https://mlsanity.com/paper/2204.11677/) (2022)
- [GraphQ IR: Unifying the Semantic Parsing of Graph Query Languages with One Intermediate Representation](https://mlsanity.com/paper/2205.12078/) (2022)
- [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)
- [History Semantic Graph Enhanced Conversational KBQA with Temporal Information Modeling](https://mlsanity.com/paper/2306.06872/) (2023)
- [Conversational Question Answering with Reformulations over Knowledge Graph](https://mlsanity.com/paper/2312.17269/) (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)
- [Reinforcement Learning for Conversational Question Answering over Knowledge Graph](https://mlsanity.com/paper/2401.08460/) (2024)
- [An expressivity analysis of hierarchical modelling in deep transformers via bounded-depth grammars](https://mlsanity.com/paper/2606.17522/) (2026)

## Abstract (arXiv)

We tackle the problem of weakly-supervised conversational Question Answering over large Knowledge Graphs using a neural semantic parsing approach. We introduce a new Logical Form (LF) grammar that can model a wide range of queries on the graph while remaining sufficiently simple to generate supervision data efficiently. Our Transformer-based model takes a JSON-like structure as input, allowing us to easily incorporate both Knowledge Graph and conversational contexts. This structured input is transformed to lists of embeddings and then fed to standard attention layers. We validate our approach, both in terms of grammar coverage and LF execution accuracy, on two publicly available datasets, CSQA and ConvQuestions, both grounded in Wikidata. On CSQA, our approach increases the coverage from 80% to 96.2%, and the LF execution accuracy from 70.6% to 75.6%, with respect to previous state-of-the-art results. On ConvQuestions, we achieve competitive results with respect to the state-of-the-art.