Semantic Parsing for Conversational Question Answering over Knowledge Graphs

Laura Perez-Beltrachini, Parag Jain, Emilio Monti, Mirella Lapata
1/28/2023
cs.CL

Official code: EdinburghNLP/SPICE (19 stars, BSD-3-Clause, last commit 2024-07-29).

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.

View on arXivView PDF

Code Implementations(1)

EdinburghNLP/SPICEOfficial100%
BSD-3-Clause

Semantic Parsing for Conversational Question Answering over Large Knowledge Graphs

190Shell, PythonOct 25, 20222 years agoBSD-3-Clause

Similar Papers

Semantic Parsing for Question Answering over Knowledge Graphs

87% match2023

Evaluating Large Language Models in Semantic Parsing for Conversational Question Answering over Knowledge Graphs

87% match1 repo32024

Conversational Semantic Parsing using Dynamic Context Graphs

84% match2023

The Role of Output Vocabulary in T2T LMs for SPARQL Semantic Parsing

82% match1 repo42023

ProKG-Dial: Progressive Multi-Turn Dialogue Construction with Domain Knowledge Graphs

82% match2025

Semantic Parsing with Candidate Expressions for Knowledge Base Question Answering

82% match1 repo2024

Cite this paper

@article{perezbeltrachini2023semantic,
  title  = {Semantic Parsing for Conversational Question Answering over Knowledge Graphs},
  author = {Laura Perez-Beltrachini and Parag Jain and Emilio Monti and Mirella Lapata},
  year   = {2023},
  eprint = {2301.12217},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2301.12217v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2301.12217.svg)](https://codeofpaper.com/paper/2301.12217)

Discussion