Question answering method for infrastructure damage information retrieval from textual data using bidirectional encoder representations from transformers

Manual searching for infrastructure damage information from large amounts of textual data requires considerable time and effort. A fast and accurate collection of damage information from such data is necessary for effective infrastructure planning. In this study, a question answering method was prop...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Automation in construction Ročník 134; s. 104061
Hlavní autoři: Kim, Yohan, Bang, Seongdeok, Sohn, Jiu, Kim, Hyoungkwan
Médium: Journal Article
Jazyk:angličtina
Vydáno: Amsterdam Elsevier B.V 01.02.2022
Elsevier BV
Témata:
Bidirectional encoder representations from transformers
Coders
Disaster management
Earthquake damage
Earthquakes
Information retrieval
Infrastructure
Infrastructure management
Model testing
Natural language processing
Question answering
Questions
Representations
Transformers
Information retrieval
Bidirectional encoder representations from transformers
Natural language processing
Question answering
Infrastructure management
Disaster management
ISSN:0926-5805, 1872-7891
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Manual searching for infrastructure damage information from large amounts of textual data requires considerable time and effort. A fast and accurate collection of damage information from such data is necessary for effective infrastructure planning. In this study, a question answering method was proposed to provide users with infrastructure damage information from textual data automatically. The proposed method relies on a natural language model called bidirectional encoder representations from transformers for information retrieval. From the 143 reports collected from the National Hurricane Center, 533 question-answer pairs were formulated. The proposed model was trained with 435 pairs and tested with the remainder. The model was also tested with 43 question-answer pairs created using earthquake-related textual data and achieved F1-scores of 90.5% and 83.6% for the hurricane and earthquake datasets, respectively. •Question answering method extracts infrastructure damage information from text data.•Proposed method based on bidirectional encoder representations from transformers.•Training and test datasets consist of 533 question-answer pairs.•F1-scores for hurricane and earthquake data are 90.5% and 83.6%, respectively.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0926-5805
1872-7891
DOI:10.1016/j.autcon.2021.104061