Semantic Parsing for Conversational Question Answering over Knowledge Graphs

TL;DR

This paper introduces a new dataset and models for semantic parsing in conversational question answering over large knowledge graphs, addressing challenges like vocabulary size and context modeling.

Contribution

It provides a novel dataset with annotated Sparql queries for conversational QA and explores two semantic parsing approaches for this task.

Findings

Developed a dataset with annotated Sparql queries for conversational QA

Highlighted challenges such as large vocabularies and context modeling

Released models and dataset for future research

Abstract

In this paper, we are interested in developing semantic parsers which understand natural language questions embedded in a conversation with a user and ground them to formal queries over definitions in a general purpose knowledge graph (KG) with very large vocabularies (covering thousands of concept names and relations, and millions of entities). To this end, we develop a dataset where user questions are annotated with Sparql parses and system answers correspond to execution results thereof. We present two different semantic parsing approaches and highlight the challenges of the task: dealing with large vocabularies, modelling conversation context, predicting queries with multiple entities, and generalising to new questions at test time. We hope our dataset will serve as useful testbed for the development of conversational semantic parsers. Our dataset and models are released at https://github.com/EdinburghNLP/SPICE.