Who are my ancestors? : retrieving family relationships from historical texts

I. Efremova; A. Montes Garcia; A.J. Bolt Iriondo; T.G.K. Calders

doi:10.1007/978-3-319-41718-9_6

Who are my ancestors? : retrieving family relationships from historical texts

I. Efremova, A. Montes Garcia, A.J. Bolt Iriondo, T.G.K. Calders

Process Analytics

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

2 Citations (Scopus)

1 Downloads (Pure)

Abstract

This paper presents an approach for automatically retrieving family relationships from a real-world collection of Dutch historical notary acts. We aim to retrieve relationships like husband - wife, parent - child, widow of, etc. Our approach includes person names extraction, reference disambiguation, candidate generation and family relationship prediction. Since we have a limited amount of training data, we evaluate different feature configurations based on the n-gram analysis. The best results were obtained by using a combination of bi-grams and trigrams of words together with the distance in words between two names. We evaluate our results for each type of the relationships in terms of precision, recall and f - score.

Original language	English
Title of host publication	Information Retrieval
Subtitle of host publication	9th Russian Summer School, RuSSIR 2015, Saint Petersburg, Russia, August 24-28, 2015, Revised Selected Papers
Editors	P. Braslavski , I. Markov, P. Pardalos, Y. Volkovich, D.I. Ignatov , S. Koltsov, O. Koltsova
Place of Publication	Berlin
Publisher	Springer
Pages	121-129
ISBN (Electronic)	978-3-319-41718-9
ISBN (Print)	978-3-319-41717-2
DOIs	https://doi.org/10.1007/978-3-319-41718-9_6
Publication status	Published - 2015

Publication series

Name	Communications in Computer and Information Science
Volume	573
ISSN (Print)	1865-0929

Access to Document

10.1007/978-3-319-41718-9_6

Cite this

Efremova, I., Montes Garcia, A., Bolt Iriondo, A. J., & Calders, T. G. K. (2015). Who are my ancestors? : retrieving family relationships from historical texts. In P. Braslavski , I. Markov, P. Pardalos, Y. Volkovich, D. I. Ignatov , S. Koltsov, & O. Koltsova (Eds.), Information Retrieval: 9th Russian Summer School, RuSSIR 2015, Saint Petersburg, Russia, August 24-28, 2015, Revised Selected Papers (pp. 121-129). (Communications in Computer and Information Science ; Vol. 573). Springer. https://doi.org/10.1007/978-3-319-41718-9_6

Efremova, I. ; Montes Garcia, A. ; Bolt Iriondo, A.J. et al. / Who are my ancestors? : retrieving family relationships from historical texts. Information Retrieval: 9th Russian Summer School, RuSSIR 2015, Saint Petersburg, Russia, August 24-28, 2015, Revised Selected Papers. editor / P. Braslavski ; I. Markov ; P. Pardalos ; Y. Volkovich ; D.I. Ignatov ; S. Koltsov ; O. Koltsova. Berlin : Springer, 2015. pp. 121-129 (Communications in Computer and Information Science ).

@inproceedings{f8e864a312eb4dd88c808ab6f5f66c0d,

title = "Who are my ancestors? : retrieving family relationships from historical texts",

abstract = "This paper presents an approach for automatically retrieving family relationships from a real-world collection of Dutch historical notary acts. We aim to retrieve relationships like husband - wife, parent - child, widow of, etc. Our approach includes person names extraction, reference disambiguation, candidate generation and family relationship prediction. Since we have a limited amount of training data, we evaluate different feature configurations based on the n-gram analysis. The best results were obtained by using a combination of bi-grams and trigrams of words together with the distance in words between two names. We evaluate our results for each type of the relationships in terms of precision, recall and f - score.",

author = "I. Efremova and {Montes Garcia}, A. and {Bolt Iriondo}, A.J. and T.G.K. Calders",

year = "2015",

doi = "10.1007/978-3-319-41718-9_6",

language = "English",

isbn = "978-3-319-41717-2",

series = "Communications in Computer and Information Science ",

publisher = "Springer",

pages = "121--129",

editor = "{Braslavski }, P. and I. Markov and P. Pardalos and Y. Volkovich and {Ignatov }, {D.I. } and S. Koltsov and O. Koltsova",

booktitle = "Information Retrieval",

address = "Germany",

}

Efremova, I, Montes Garcia, A, Bolt Iriondo, AJ & Calders, TGK 2015, Who are my ancestors? : retrieving family relationships from historical texts. in P Braslavski , I Markov, P Pardalos, Y Volkovich, DI Ignatov , S Koltsov & O Koltsova (eds), Information Retrieval: 9th Russian Summer School, RuSSIR 2015, Saint Petersburg, Russia, August 24-28, 2015, Revised Selected Papers. Communications in Computer and Information Science , vol. 573, Springer, Berlin, pp. 121-129. https://doi.org/10.1007/978-3-319-41718-9_6

Who are my ancestors? : retrieving family relationships from historical texts. / Efremova, I.; Montes Garcia, A.; Bolt Iriondo, A.J. et al.
Information Retrieval: 9th Russian Summer School, RuSSIR 2015, Saint Petersburg, Russia, August 24-28, 2015, Revised Selected Papers. ed. / P. Braslavski ; I. Markov; P. Pardalos; Y. Volkovich; D.I. Ignatov ; S. Koltsov; O. Koltsova. Berlin: Springer, 2015. p. 121-129 (Communications in Computer and Information Science ; Vol. 573).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Who are my ancestors? : retrieving family relationships from historical texts

AU - Efremova, I.

AU - Montes Garcia, A.

AU - Bolt Iriondo, A.J.

AU - Calders, T.G.K.

PY - 2015

Y1 - 2015

N2 - This paper presents an approach for automatically retrieving family relationships from a real-world collection of Dutch historical notary acts. We aim to retrieve relationships like husband - wife, parent - child, widow of, etc. Our approach includes person names extraction, reference disambiguation, candidate generation and family relationship prediction. Since we have a limited amount of training data, we evaluate different feature configurations based on the n-gram analysis. The best results were obtained by using a combination of bi-grams and trigrams of words together with the distance in words between two names. We evaluate our results for each type of the relationships in terms of precision, recall and f - score.

AB - This paper presents an approach for automatically retrieving family relationships from a real-world collection of Dutch historical notary acts. We aim to retrieve relationships like husband - wife, parent - child, widow of, etc. Our approach includes person names extraction, reference disambiguation, candidate generation and family relationship prediction. Since we have a limited amount of training data, we evaluate different feature configurations based on the n-gram analysis. The best results were obtained by using a combination of bi-grams and trigrams of words together with the distance in words between two names. We evaluate our results for each type of the relationships in terms of precision, recall and f - score.

U2 - 10.1007/978-3-319-41718-9_6

DO - 10.1007/978-3-319-41718-9_6

M3 - Conference contribution

SN - 978-3-319-41717-2

T3 - Communications in Computer and Information Science

SP - 121

EP - 129

BT - Information Retrieval

A2 - Braslavski , P.

A2 - Markov, I.

A2 - Pardalos, P.

A2 - Volkovich, Y.

A2 - Ignatov , D.I.

A2 - Koltsov, S.

A2 - Koltsova, O.

PB - Springer

CY - Berlin

ER -

Efremova I, Montes Garcia A, Bolt Iriondo AJ, Calders TGK. Who are my ancestors? : retrieving family relationships from historical texts. In Braslavski P, Markov I, Pardalos P, Volkovich Y, Ignatov DI, Koltsov S, Koltsova O, editors, Information Retrieval: 9th Russian Summer School, RuSSIR 2015, Saint Petersburg, Russia, August 24-28, 2015, Revised Selected Papers. Berlin: Springer. 2015. p. 121-129. (Communications in Computer and Information Science ). doi: 10.1007/978-3-319-41718-9_6

Who are my ancestors? : retrieving family relationships from historical texts

Abstract

Publication series

Access to Document

Fingerprint

Cite this