The automatic categorisation of space mission requirements for the Design Engineering Assistant

Research output: Contribution to conferencePaper

Abstract

To enhance Knowledge Reuse in the field of space mission design, the implementation of Information Retrieval (IR) is key. Topic Modeling (TM) is used to identify, learn and extract topics from a corpus of documents, and can therefore support several IR tasks such as categorisation. This study relies on a common TM method, Latent Dirichlet Allocation (LDA), a probability-based approach. An extensive Wikipedia-based corpus focused on space mission design is collected, parsed, preprocessed, and used to train a general ’Space Mission Design’ LDA model. The LDA model is optimised based on the perplexity measure for a range of topics numbers. The topics dictionaries of the retained model are labelled by human annotators, with labels corresponding to spacecraft subsystems. The performances of the general model are evaluated against a set of space mission requirements with a categorisation task. The general model is then used as a base to generate specific LDA models focused on one topic, or spacecraft subsystem. The general LDA model developed in this study proves to be a solid base for the generation of focused LDA models, yielding very high accuracy scores and Mean Reciprocal Ranking.Finally, a semi-supervised LDA model, fed with lexical priors is trained, leading to improved performances of a general model
Original languageEnglish
Number of pages11
Publication statusPublished - 25 Oct 2019
Event70th International Astronautical Congress - Washington D.C., United States
Duration: 21 Oct 201925 Oct 2019
https://www.iac2019.org/

Conference

Conference70th International Astronautical Congress
Abbreviated titleIAC
CountryUnited States
CityWashington D.C.
Period21/10/1925/10/19
Internet address

Fingerprint

Information retrieval
Spacecraft
Glossaries
Labels

Keywords

  • topic modeling
  • LDA
  • machine learning
  • categorisation
  • mission requirements
  • visual assistant

Cite this

Berquand, A., McDonald, I., Riccardi, A., & Moshfeghi, Y. (2019). The automatic categorisation of space mission requirements for the Design Engineering Assistant. Paper presented at 70th International Astronautical Congress, Washington D.C., United States.
Berquand, Audrey ; McDonald, Iain ; Riccardi, Annalisa ; Moshfeghi, Yashar. / The automatic categorisation of space mission requirements for the Design Engineering Assistant. Paper presented at 70th International Astronautical Congress, Washington D.C., United States.11 p.
@conference{70d1a911ff0543fd8f8ed513f07239e1,
title = "The automatic categorisation of space mission requirements for the Design Engineering Assistant",
abstract = "To enhance Knowledge Reuse in the field of space mission design, the implementation of Information Retrieval (IR) is key. Topic Modeling (TM) is used to identify, learn and extract topics from a corpus of documents, and can therefore support several IR tasks such as categorisation. This study relies on a common TM method, Latent Dirichlet Allocation (LDA), a probability-based approach. An extensive Wikipedia-based corpus focused on space mission design is collected, parsed, preprocessed, and used to train a general ’Space Mission Design’ LDA model. The LDA model is optimised based on the perplexity measure for a range of topics numbers. The topics dictionaries of the retained model are labelled by human annotators, with labels corresponding to spacecraft subsystems. The performances of the general model are evaluated against a set of space mission requirements with a categorisation task. The general model is then used as a base to generate specific LDA models focused on one topic, or spacecraft subsystem. The general LDA model developed in this study proves to be a solid base for the generation of focused LDA models, yielding very high accuracy scores and Mean Reciprocal Ranking.Finally, a semi-supervised LDA model, fed with lexical priors is trained, leading to improved performances of a general model",
keywords = "topic modeling, LDA, machine learning, categorisation, mission requirements, visual assistant",
author = "Audrey Berquand and Iain McDonald and Annalisa Riccardi and Yashar Moshfeghi",
year = "2019",
month = "10",
day = "25",
language = "English",
note = "70th International Astronautical Congress, IAC ; Conference date: 21-10-2019 Through 25-10-2019",
url = "https://www.iac2019.org/",

}

Berquand, A, McDonald, I, Riccardi, A & Moshfeghi, Y 2019, 'The automatic categorisation of space mission requirements for the Design Engineering Assistant' Paper presented at 70th International Astronautical Congress, Washington D.C., United States, 21/10/19 - 25/10/19, .

The automatic categorisation of space mission requirements for the Design Engineering Assistant. / Berquand, Audrey; McDonald, Iain ; Riccardi, Annalisa; Moshfeghi, Yashar.

2019. Paper presented at 70th International Astronautical Congress, Washington D.C., United States.

Research output: Contribution to conferencePaper

TY - CONF

T1 - The automatic categorisation of space mission requirements for the Design Engineering Assistant

AU - Berquand, Audrey

AU - McDonald, Iain

AU - Riccardi, Annalisa

AU - Moshfeghi, Yashar

PY - 2019/10/25

Y1 - 2019/10/25

N2 - To enhance Knowledge Reuse in the field of space mission design, the implementation of Information Retrieval (IR) is key. Topic Modeling (TM) is used to identify, learn and extract topics from a corpus of documents, and can therefore support several IR tasks such as categorisation. This study relies on a common TM method, Latent Dirichlet Allocation (LDA), a probability-based approach. An extensive Wikipedia-based corpus focused on space mission design is collected, parsed, preprocessed, and used to train a general ’Space Mission Design’ LDA model. The LDA model is optimised based on the perplexity measure for a range of topics numbers. The topics dictionaries of the retained model are labelled by human annotators, with labels corresponding to spacecraft subsystems. The performances of the general model are evaluated against a set of space mission requirements with a categorisation task. The general model is then used as a base to generate specific LDA models focused on one topic, or spacecraft subsystem. The general LDA model developed in this study proves to be a solid base for the generation of focused LDA models, yielding very high accuracy scores and Mean Reciprocal Ranking.Finally, a semi-supervised LDA model, fed with lexical priors is trained, leading to improved performances of a general model

AB - To enhance Knowledge Reuse in the field of space mission design, the implementation of Information Retrieval (IR) is key. Topic Modeling (TM) is used to identify, learn and extract topics from a corpus of documents, and can therefore support several IR tasks such as categorisation. This study relies on a common TM method, Latent Dirichlet Allocation (LDA), a probability-based approach. An extensive Wikipedia-based corpus focused on space mission design is collected, parsed, preprocessed, and used to train a general ’Space Mission Design’ LDA model. The LDA model is optimised based on the perplexity measure for a range of topics numbers. The topics dictionaries of the retained model are labelled by human annotators, with labels corresponding to spacecraft subsystems. The performances of the general model are evaluated against a set of space mission requirements with a categorisation task. The general model is then used as a base to generate specific LDA models focused on one topic, or spacecraft subsystem. The general LDA model developed in this study proves to be a solid base for the generation of focused LDA models, yielding very high accuracy scores and Mean Reciprocal Ranking.Finally, a semi-supervised LDA model, fed with lexical priors is trained, leading to improved performances of a general model

KW - topic modeling

KW - LDA

KW - machine learning

KW - categorisation

KW - mission requirements

KW - visual assistant

UR - https://www.iac2019.org/

M3 - Paper

ER -

Berquand A, McDonald I, Riccardi A, Moshfeghi Y. The automatic categorisation of space mission requirements for the Design Engineering Assistant. 2019. Paper presented at 70th International Astronautical Congress, Washington D.C., United States.