What question did this study set out to answer?

Determine whether machine learning sequence tagging models can reliably extract named entities and geographic locations from unstructured Portuguese archival finding aids.

August 9, 2015Open Access

Bidirectional LSTM-CRF Models for Sequence Tagging

View Full Paper

Ask AI

Bookmark

Authors

KYKai YuShanghai Jiao Tong University

Discussion

Member takes

Implication

Experimental evaluation demonstrates the performance of sequence tagging models in Portuguese archival finding aids, highlighting their potential for automated index creation.

Key Points

Determine whether machine learning sequence tagging models can reliably extract named entities and geographic locations from unstructured Portuguese archival finding aids.
Created dedicated annotated datasets derived from natural language finding aids in Portuguese archival management platforms such as Digitarq and Archeevo.
Trained and evaluated multiple machine learning sequence tagging algorithms across datasets, measuring precision and accuracy.
Evaluated model precision and accuracy to establish benchmarks for detecting person names, geographic locations, and dates within archival text.
Demonstrated the practical viability of using sequence tagging outputs to generate automated toponymic and anthroponomic indexes for historical catalogs.

Cite This Study

Kai Yu (2015) studied this question.

synapsesocial.com/papers/6a7cf803a5385839bca1e824 https://doi.org/10.4230/oasics.slate.2021.8

View Full Paper

Ask AI

Bookmark

Implication

Experimental evaluation demonstrates the performance of sequence tagging models in Portuguese archival finding aids, highlighting their potential for automated index creation.

Bidirectional LSTM-CRF Models for Sequence Tagging

Discussion

Member takes

Implication

Key Points

Cite This Study

Bidirectional LSTM-CRF Models for Sequence Tagging

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider