Knowledge Base Question Answering for Space Debris Queries
- URL: http://arxiv.org/abs/2305.19734v1
- Date: Wed, 31 May 2023 10:55:41 GMT
- Title: Knowledge Base Question Answering for Space Debris Queries
- Authors: Paul Darm, Antonio Valerio Miceli-Barone, Shay B. Cohen, Annalisa
Riccardi
- Abstract summary: We present a system, developed for the European Space Agency (ESA), that can answer complex natural language queries.
Our system is based on a pipeline which first generates a sequence of basic database operations, called a %program sketch, from a natural language question.
This pipeline decomposition approach enables us to train the system by leveraging out-of-domain data and semi-synthetic data generated by GPT-3.
- Score: 24.37269129187282
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: 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 %program
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 \url{https://github.com/PaulDrm/DISCOSQA}.
Related papers
- Boost, Disentangle, and Customize: A Robust System2-to-System1 Pipeline for Code Generation [58.799397354312596]
Large language models (LLMs) have demonstrated remarkable capabilities in various domains, particularly in system 1 tasks.
Recent research on System2-to-System1 methods surge, exploring the System 2 reasoning knowledge via inference-time computation.
In this paper, we focus on code generation, which is a representative System 2 task, and identify two primary challenges.
arXiv Detail & Related papers (2025-02-18T03:20:50Z) - GEE-OPs: An Operator Knowledge Base for Geospatial Code Generation on the Google Earth Engine Platform Powered by Large Language Models [0.562479170374811]
We propose a framework for building a operator knowledge base tailored to the Google Earth Engine (GEE) JavaScript API.
This framework consists of an operator syntax knowledge table, an operator relationship frequency table, an operator frequent pattern knowledge table, and an operator relationship chain knowledge table.
We show that the framework achieves over 90% accuracy, recall, and F1 score in operator knowledge extraction.
arXiv Detail & Related papers (2024-12-07T08:50:24Z) - The S2 Hierarchical Discrete Global Grid as a Nexus for Data Representation, Integration, and Querying Across Geospatial Knowledge Graphs [4.358099505067763]
This paper outlines the implementation of Google's S2 Geometry within KnowWhereGraph.
Ultimately, this work demonstrates the potential of DGGS frameworks, particularly S2, for building scalable GeoKGs.
arXiv Detail & Related papers (2024-10-18T18:30:05Z) - Developing PUGG for Polish: A Modern Approach to KBQA, MRC, and IR Dataset Construction [43.045596895389345]
We introduce a modern, semi-automated approach for creating datasets, encompassing tasks such as KBQA, Machine Reading (MRC), and Information Retrieval (IR)
We provide a comprehensive implementation, insightful findings, detailed statistics, and evaluation of baseline models.
arXiv Detail & Related papers (2024-08-05T09:23:49Z) - How to Understand Whole Software Repository? [64.19431011897515]
An excellent understanding of the whole repository will be the critical path to Automatic Software Engineering (ASE)
We develop a novel method named RepoUnderstander by guiding agents to comprehensively understand the whole repositories.
To better utilize the repository-level knowledge, we guide the agents to summarize, analyze, and plan.
arXiv Detail & Related papers (2024-06-03T15:20:06Z) - DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain
Question Answering over Knowledge Base and Text [73.68051228972024]
Large Language Models (LLMs) have exhibited impressive generation capabilities, but they suffer from hallucinations when relying on their internal knowledge.
Retrieval-augmented LLMs have emerged as a potential solution to ground LLMs in external knowledge.
arXiv Detail & Related papers (2023-10-31T04:37:57Z) - A Simple Baseline for Knowledge-Based Visual Question Answering [78.00758742784532]
This paper is on the problem of Knowledge-Based Visual Question Answering (KB-VQA)
Our main contribution in this paper is to propose a much simpler and readily reproducible pipeline.
Contrary to recent approaches, our method is training-free, does not require access to external databases or APIs, and achieves state-of-the-art accuracy on the OK-VQA and A-OK-VQA datasets.
arXiv Detail & Related papers (2023-10-20T15:08:17Z) - Semantic Web Enabled Geographic Question Answering Framework: GeoTR [0.0]
In this study, a question answering framework that converts Turkish natural language input into SPARQL queries in the geographical domain is proposed.
A novel Turkish ontology, which covers a 10th grade geography lesson named Spatial Synthesis Turkey, has been developed to be used as a linked data provider.
A hybrid system architecture that combines natural language processing techniques with linked data technologies to generate answers is also proposed.
arXiv Detail & Related papers (2023-01-11T23:20:43Z) - SpaceQA: Answering Questions about the Design of Space Missions and
Space Craft Concepts [57.012600276711005]
We present SpaceQA, to the best of our knowledge the first open-domain QA system in Space mission design.
SpaceQA is part of an initiative by the European Space Agency (ESA) to facilitate the access, sharing and reuse of information about Space mission design.
arXiv Detail & Related papers (2022-10-07T09:41:39Z) - Data-to-Value: An Evaluation-First Methodology for Natural Language
Projects [3.9378507882929554]
"Data to Value" (D2V) is a new methodology for big data text analytics projects.
It is guided by a detailed catalog of questions in order to avoid a disconnect between big data text analytics project team and the topic.
arXiv Detail & Related papers (2022-01-19T17:04:52Z) - Differentiable Reasoning over a Virtual Knowledge Base [156.94984221342716]
We consider the task of answering complex multi-hop questions using a corpus as a virtual knowledge base (KB)
In particular, we describe a neural module, DrKIT, that traverses textual data like a KB, softly following paths of relations between mentions of entities in the corpus.
DrKIT is very efficient, processing 10-100x more queries per second than existing multi-hop systems.
arXiv Detail & Related papers (2020-02-25T03:13:32Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.