# Answering Conversational Questions on Structured Data without Logical Forms

arXiv: https://arxiv.org/abs/1908.11787 · HTML: https://mlsanity.com/paper/1908.11787/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Aug 2019.

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

- [TAPEX: Table Pre-training via Learning a Neural SQL Executor](https://mlsanity.com/paper/2107.07653/) (2021)
- [TableBench: A Comprehensive and Complex Benchmark for Table Question Answering](https://mlsanity.com/paper/2408.09174/) (2024)
- [TableFormer: Robust Transformer Modeling for Table-Text Encoding](https://mlsanity.com/paper/2203.00274/) (2022)
- [Neural Approaches to Conversational Information Retrieval](https://mlsanity.com/paper/2201.05176/) (2022)
- [A Survey on Table Question Answering: Recent Advances](https://mlsanity.com/paper/2207.05270/) (2022)
- [Table-R1: Region-based Reinforcement Learning for Table Understanding](https://mlsanity.com/paper/2505.12415/) (2025)
- [HYTREL: Hypergraph-enhanced Tabular Data Representation Learning](https://mlsanity.com/paper/2307.08623/) (2023)
- [Conversational Question Answering: A Survey](https://mlsanity.com/paper/2106.00874/) (2021)
- [Conversational Question Answering on Heterogeneous Sources](https://mlsanity.com/paper/2204.11677/) (2022)
- [Representations for Question Answering from Documents with Tables and Text](https://mlsanity.com/paper/2101.10573/) (2021)
- [Table-To-Text generation and pre-training with TabT5](https://mlsanity.com/paper/2210.09162/) (2022)
- [Reinforcement Learning from Reformulations in Conversational Question Answering over Knowledge Graphs](https://mlsanity.com/paper/2105.04850/) (2021)
- [DiSCoMaT: Distantly Supervised Composition Extraction from Tables in Materials Science Articles](https://mlsanity.com/paper/2207.01079/) (2022)
- [From Zero to Hero: Examining the Power of Symbolic Tasks in Instruction Tuning](https://mlsanity.com/paper/2304.07995/) (2023)
- [RealHiTBench: A Comprehensive Realistic Hierarchical Table Benchmark for Evaluating LLM-Based Table Analysis](https://mlsanity.com/paper/2506.13405/) (2025)
- [Interactive Question Answering Systems: Literature Review](https://mlsanity.com/paper/2209.01621/) (2022)
- [Mixture-of-Minds: Multi-Agent Reinforcement Learning for Table Understanding](https://mlsanity.com/paper/2510.20176/) (2025)
- [From Features to Structure: Task-Aware Graph Construction for Relational and Tabular Learning with GNNs](https://mlsanity.com/paper/2506.02243/) (2025)
- [TableQuery: Querying tabular data with natural language](https://mlsanity.com/paper/2202.00454/) (2022)
- [Document Intelligence in the Era of Large Language Models: A Survey](https://mlsanity.com/paper/2510.13366/) (2025)
- [Enhancing Open-Domain Table Question Answering via Syntax- and Structure-aware Dense Retrieval](https://mlsanity.com/paper/2309.10506/) (2023)
- [How Accurate Are LLMs at Multi-Question Answering on Conversational Transcripts?](https://mlsanity.com/paper/2509.21732/) (2025)
- [Training Table Question Answering via SQL Query Decomposition](https://mlsanity.com/paper/2402.13288/) (2024)
- [Around the GLOBE: Numerical Aggregation Question-Answering on Heterogeneous Genealogical Knowledge Graphs with Deep Neural Networks](https://mlsanity.com/paper/2307.16208/) (2023)

## Abstract (arXiv)

We present a novel approach to answering sequential questions based on structured objects such as knowledge bases or tables without using a logical form as an intermediate representation. We encode tables as graphs using a graph neural network model based on the Transformer architecture. The answers are then selected from the encoded graph using a pointer network. This model is appropriate for processing conversations around structured data, where the attention mechanism that selects the answers to a question can also be used to resolve conversational references. We demonstrate the validity of this approach with competitive results on the Sequential Question Answering (SQA) task (Iyyer et al., 2017).