# Knowledge-Aware Conversational Semantic Parsing Over Web Tables

arXiv: https://arxiv.org/abs/1809.04271 · HTML: https://mlsanity.com/paper/1809.04271/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Sep 2018.

## Built on by (most cited first, 6 of 6)

- [TAPEX: Table Pre-training via Learning a Neural SQL Executor](https://mlsanity.com/paper/2107.07653/) (2021)
- [Crossing the Conversational Chasm: A Primer on Natural Language Processing for Multilingual Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2104.08570/) (2021)
- [RETRONLU: Retrieval Augmented Task-Oriented Semantic Parsing](https://mlsanity.com/paper/2109.10410/) (2021)
- [From Zero to Hero: Examining the Power of Symbolic Tasks in Instruction Tuning](https://mlsanity.com/paper/2304.07995/) (2023)
- [BreakingBERT@IITK at SemEval-2021 Task 9 : Statement Verification and Evidence Finding with Tables](https://mlsanity.com/paper/2104.03071/) (2021)
- [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)

Conversational semantic parsing over tables requires knowledge acquiring and reasoning abilities, which have not been well explored by current state-of-the-art approaches. Motivated by this fact, we propose a knowledge-aware semantic parser to improve parsing performance by integrating various types of knowledge. In this paper, we consider three types of knowledge, including grammar knowledge, expert knowledge, and external resource knowledge. First, grammar knowledge empowers the model to effectively replicate previously generated logical form, which effectively handles the co-reference and ellipsis phenomena in conversation Second, based on expert knowledge, we propose a decomposable model, which is more controllable compared with traditional end-to-end models that put all the burdens of learning on trial-and-error in an end-to-end way. Third, external resource knowledge, i.e., provided by a pre-trained language model or an entity typing model, is used to improve the representation of question and table for a better semantic understanding. We conduct experiments on the SequentialQA dataset. Results show that our knowledge-aware model outperforms the state-of-the-art approaches. Incremental experimental results also prove the usefulness of various knowledge. Further analysis shows that our approach has the ability to derive the meaning representation of a context-dependent utterance by leveraging previously generated outcomes.