Knowledge Base Question Answering for Space Debris Queries

05/31/2023
by   Paul Darm, et al.
0

Space agencies execute complex satellite operations that need to be supported by the technical knowledge contained in their extensive information systems. Knowledge bases (KB) are an effective way of storing and accessing such information at scale. In this work we present a system, developed for the European Space Agency (ESA), that can answer complex natural language queries, to support engineers in accessing the information contained in a KB that models the orbital space debris environment. Our system is based on a pipeline which first generates a sequence of basic database operations, called a sketch, from a natural language question, then specializes the sketch into a concrete query program with mentions of entities, attributes and relations, and finally executes the program against the database. This pipeline decomposition approach enables us to train the system by leveraging out-of-domain data and semi-synthetic data generated by GPT-3, thus reducing overfitting and shortcut learning even with limited amount of in-domain training data. Our code can be found at <https://github.com/PaulDrm/DISCOSQA>.

READ FULL TEXT

page 10

page 13

research
10/29/2020

Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learning

A compelling approach to complex question answering is to convert the qu...
research
11/15/2018

End-to-End Learning for Answering Structured Queries Directly over Text

Structured queries expressed in languages (such as SQL, SPARQL, or XQuer...
research
10/29/2020

Few-Shot Complex Knowledge Base Question Answering via Meta Reinforcement Learning

Complex question-answering (CQA) involves answering complex natural-lang...
research
08/23/2023

FlexKBQA: A Flexible LLM-Powered Framework for Few-Shot Knowledge Base Question Answering

Knowledge base question answering (KBQA) is a critical yet challenging t...
research
07/17/2019

Learning Representation Mapping for Relation Detection in Knowledge Base Question Answering

Relation detection is a core step in many natural language process appli...
research
07/08/2022

Crake: Causal-Enhanced Table-Filler for Question Answering over Large Scale Knowledge Base

Semantic parsing solves knowledge base (KB) question answering (KBQA) by...
research
11/10/2022

Wikidata-lite for Knowledge Extraction and Exploration

Wikidata is the largest collaborative general knowledge graph supported ...

Please sign up or login with your details

Forgot password? Click here to reset