| Texto completo | |
| Autor(es): |
Pol Goncalves, Flavio Jaime
;
de Oliveira Carmo, Vinicius Cleves
;
de Melo, Vinicius Toquetti
;
Cunha, Rodrigo da Silva
;
Santos, Ismael H. F.
;
Barreira, Rodrigo Augusto
;
Cugnasca, Carlos Eduardo
;
Cozman, Fabio Gagliardi
;
Gomi, Edson Satoshi
;
Amer Soc Mech Engineers
Número total de Autores: 10
|
| Tipo de documento: | Artigo Científico |
| Fonte: | PROCEEDINGS OF ASME 2021 40TH INTERNATIONAL CONFERENCE ON OCEAN, OFFSHORE AND ARCTIC ENGINEERING (OMAE2021), VOL 1; v. N/A, p. 9-pg., 2021-01-01. |
| Resumo | |
This paper presents a computing pipeline architecture for semantic search in the domain of Offshore Engineering. The proposed system combines modules such as document retriever, passage retriever, and answer extractor to produce textual responses to queries in natural language such as: "What FPSO motion is mostly affected by viscous damping?" Such responses are often needed in Offshore Engineering activities, and linguistic techniques such as those based on inverted indexes with a syntactic focus tend to perform poorly. Instead, this research explores semantic techniques that take into account the meaning of words in the domain of Offshore Engineering. This paper describes a Linguistic QA pipeline architecture built that provides a way to retrieve answers instantly from a collection of 13,000 unstructured technical documents about Offshore Engineering, reports the achieved results and future work. This paper also presents additional modules under construction that exploit Neural Networks and ontologies approaches for semantic search in the domain of Offshore Engineering. (AU) | |
| Processo FAPESP: | 19/07665-4 - Centro de Inteligência Artificial |
| Beneficiário: | Fabio Gagliardi Cozman |
| Modalidade de apoio: | Auxílio à Pesquisa - Programa eScience e Data Science - Centros de Pesquisa em Engenharia |