Semantic and Topological Graphs for Patent Retrieval

André Rattinger, Jean-Marie Le Goff, Christian Gütl

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

Abstract

Information Retrieval often relies on the indexed terms that occur in the documents, but rarely is the available associated metadata processed to aid in the retrieval process. In addition to this, the associated metadata is often interlinked data that can be the basis for graphs, such as citation or coauthorship graphs. One of these types of graphs can be build from the classification systems. Classification systems aim to organize the knowledge in the documents and make retrieval easier. This work utilizes two types of graphs that were developed out of the classification systems in previous work: Topological and semantic graphs. The topological graph is based on the classification system assigned by experts and the co-classification that can be found with those. The semantic graph is based on the textual content of the documents and the relations that can be found when vectors are assigned to the classes based on this content. The structure and weights of those graphs can then be utilized to supplement the retrieval process and re-rank the result lists. In this work we show how those graphs are a valuable addition to improve performance in patent retrieval tasks and how different versions of this retrieval process compare to each other.
Original languageEnglish
Title of host publication2019 Sixth International Conference on Social Networks Analysis, Management and Security (SNAMS)
PublisherIEEE Xplore
Pages175 - 180
ISBN (Electronic)978-1-7281-2946-4
Publication statusPublished - 16 Dec 2019
Event2019 Sixth International Conference on Social Networks Analysis, Management and Security (SNAMS) - Granada, Spain
Duration: 22 Oct 201825 Oct 2019
http://emergingtechnet.org/SNAMS2019/

Conference

Conference2019 Sixth International Conference on Social Networks Analysis, Management and Security (SNAMS)
CountrySpain
CityGranada
Period22/10/1825/10/19
Internet address

Fingerprint

Semantics
Metadata
Information retrieval

Cite this

Rattinger, A., Le Goff, J-M., & Gütl, C. (2019). Semantic and Topological Graphs for Patent Retrieval. In 2019 Sixth International Conference on Social Networks Analysis, Management and Security (SNAMS) (pp. 175 - 180). IEEE Xplore.

Semantic and Topological Graphs for Patent Retrieval. / Rattinger, André; Le Goff, Jean-Marie; Gütl, Christian.

2019 Sixth International Conference on Social Networks Analysis, Management and Security (SNAMS). IEEE Xplore, 2019. p. 175 - 180.

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

Rattinger, A, Le Goff, J-M & Gütl, C 2019, Semantic and Topological Graphs for Patent Retrieval. in 2019 Sixth International Conference on Social Networks Analysis, Management and Security (SNAMS). IEEE Xplore, pp. 175 - 180, 2019 Sixth International Conference on Social Networks Analysis, Management and Security (SNAMS), Granada, Spain, 22/10/18.
Rattinger A, Le Goff J-M, Gütl C. Semantic and Topological Graphs for Patent Retrieval. In 2019 Sixth International Conference on Social Networks Analysis, Management and Security (SNAMS). IEEE Xplore. 2019. p. 175 - 180
Rattinger, André ; Le Goff, Jean-Marie ; Gütl, Christian. / Semantic and Topological Graphs for Patent Retrieval. 2019 Sixth International Conference on Social Networks Analysis, Management and Security (SNAMS). IEEE Xplore, 2019. pp. 175 - 180
@inproceedings{1eccfd1b58e94af2bc6cae7ac05fa711,
title = "Semantic and Topological Graphs for Patent Retrieval",
abstract = "Information Retrieval often relies on the indexed terms that occur in the documents, but rarely is the available associated metadata processed to aid in the retrieval process. In addition to this, the associated metadata is often interlinked data that can be the basis for graphs, such as citation or coauthorship graphs. One of these types of graphs can be build from the classification systems. Classification systems aim to organize the knowledge in the documents and make retrieval easier. This work utilizes two types of graphs that were developed out of the classification systems in previous work: Topological and semantic graphs. The topological graph is based on the classification system assigned by experts and the co-classification that can be found with those. The semantic graph is based on the textual content of the documents and the relations that can be found when vectors are assigned to the classes based on this content. The structure and weights of those graphs can then be utilized to supplement the retrieval process and re-rank the result lists. In this work we show how those graphs are a valuable addition to improve performance in patent retrieval tasks and how different versions of this retrieval process compare to each other.",
author = "Andr{\'e} Rattinger and {Le Goff}, Jean-Marie and Christian G{\"u}tl",
year = "2019",
month = "12",
day = "16",
language = "English",
pages = "175 -- 180",
booktitle = "2019 Sixth International Conference on Social Networks Analysis, Management and Security (SNAMS)",
publisher = "IEEE Xplore",

}

TY - GEN

T1 - Semantic and Topological Graphs for Patent Retrieval

AU - Rattinger, André

AU - Le Goff, Jean-Marie

AU - Gütl, Christian

PY - 2019/12/16

Y1 - 2019/12/16

N2 - Information Retrieval often relies on the indexed terms that occur in the documents, but rarely is the available associated metadata processed to aid in the retrieval process. In addition to this, the associated metadata is often interlinked data that can be the basis for graphs, such as citation or coauthorship graphs. One of these types of graphs can be build from the classification systems. Classification systems aim to organize the knowledge in the documents and make retrieval easier. This work utilizes two types of graphs that were developed out of the classification systems in previous work: Topological and semantic graphs. The topological graph is based on the classification system assigned by experts and the co-classification that can be found with those. The semantic graph is based on the textual content of the documents and the relations that can be found when vectors are assigned to the classes based on this content. The structure and weights of those graphs can then be utilized to supplement the retrieval process and re-rank the result lists. In this work we show how those graphs are a valuable addition to improve performance in patent retrieval tasks and how different versions of this retrieval process compare to each other.

AB - Information Retrieval often relies on the indexed terms that occur in the documents, but rarely is the available associated metadata processed to aid in the retrieval process. In addition to this, the associated metadata is often interlinked data that can be the basis for graphs, such as citation or coauthorship graphs. One of these types of graphs can be build from the classification systems. Classification systems aim to organize the knowledge in the documents and make retrieval easier. This work utilizes two types of graphs that were developed out of the classification systems in previous work: Topological and semantic graphs. The topological graph is based on the classification system assigned by experts and the co-classification that can be found with those. The semantic graph is based on the textual content of the documents and the relations that can be found when vectors are assigned to the classes based on this content. The structure and weights of those graphs can then be utilized to supplement the retrieval process and re-rank the result lists. In this work we show how those graphs are a valuable addition to improve performance in patent retrieval tasks and how different versions of this retrieval process compare to each other.

M3 - Conference contribution

SP - 175

EP - 180

BT - 2019 Sixth International Conference on Social Networks Analysis, Management and Security (SNAMS)

PB - IEEE Xplore

ER -