Learning knowledge graph embeddings with type regularizer
Learning relations based on evidence from knowledge bases relies on processing the available relation instances. Many relations, however, have clear domain and range, which we hypothesize could help learn a better, more generalizing, model. We include such information in the RESCAL model in the form...
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Dokumenttyp: | Article (Journal) Kapitel/Artikel |
| Sprache: | Englisch |
| Veröffentlicht: |
2 Mar 2018
|
| In: |
Arxiv
|
| Online-Zugang: | Verlag, Volltext: http://arxiv.org/abs/1706.09278
|
| Verfasserangaben: | Bhushan Kotnis and Vivi Nastase |
MARC
| LEADER | 00000caa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 1675677042 | ||
| 003 | DE-627 | ||
| 005 | 20220816215716.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 190902s2018 xx |||||o 00| ||eng c | ||
| 035 | |a (DE-627)1675677042 | ||
| 035 | |a (DE-599)KXP1675677042 | ||
| 035 | |a (OCoLC)1341238832 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 28 |2 sdnb | ||
| 100 | 1 | |a Kotnis, Bhushan |e VerfasserIn |0 (DE-588)1190653478 |0 (DE-627)1669204197 |4 aut | |
| 245 | 1 | 0 | |a Learning knowledge graph embeddings with type regularizer |c Bhushan Kotnis and Vivi Nastase |
| 264 | 1 | |c 2 Mar 2018 | |
| 300 | |a 6 | ||
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Gesehen am 02.09.2019 | ||
| 520 | |a Learning relations based on evidence from knowledge bases relies on processing the available relation instances. Many relations, however, have clear domain and range, which we hypothesize could help learn a better, more generalizing, model. We include such information in the RESCAL model in the form of a regularization factor added to the loss function that takes into account the types (categories) of the entities that appear as arguments to relations in the knowledge base. We note increased performance compared to the baseline model in terms of mean reciprocal rank and hitsN, N = 1, 3, 10. Furthermore, we discover scenarios that significantly impact the effectiveness of the type regularizer. | ||
| 650 | 4 | |a Computer Science - Artificial Intelligence | |
| 700 | 1 | |a Nastase, Vivi |d 1975- |e VerfasserIn |0 (DE-588)1041331800 |0 (DE-627)76701880X |0 (DE-576)393039927 |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Arxiv |d Ithaca, NY : Cornell University, 1991 |g (2018) |h Online-Ressource |w (DE-627)509006531 |w (DE-600)2225896-6 |w (DE-576)28130436X |7 nnas |a Learning knowledge graph embeddings with type regularizer |
| 773 | 1 | 8 | |g year:2018 |g extent:6 |a Learning knowledge graph embeddings with type regularizer |
| 787 | 0 | 8 | |i Forschungsdaten |a Kotnis, Bhushan |t KGE algorithms |d Heidelberg : Universität, 2019 |h 1 Online-Ressource (1 File) |w (DE-627)1675675104 |
| 856 | 4 | 0 | |u http://arxiv.org/abs/1706.09278 |x Verlag |3 Volltext |
| 951 | |a AR | ||
| 992 | |a 20190902 | ||
| 993 | |a Article | ||
| 994 | |a 2018 | ||
| 998 | |g 1041331800 |a Nastase, Vivi |m 1041331800:Nastase, Vivi |d 90000 |d 90500 |e 90000PN1041331800 |e 90500PN1041331800 |k 0/90000/ |k 1/90000/90500/ |p 2 |y j | ||
| 998 | |g 1190653478 |a Kotnis, Bhushan |m 1190653478:Kotnis, Bhushan |d 90000 |d 90500 |e 90000PK1190653478 |e 90500PK1190653478 |k 0/90000/ |k 1/90000/90500/ |p 1 |x j | ||
| 999 | |a KXP-PPN1675677042 |e 351084985X | ||
| BIB | |a Y | ||
| JSO | |a {"title":[{"title_sort":"Learning knowledge graph embeddings with type regularizer","title":"Learning knowledge graph embeddings with type regularizer"}],"person":[{"display":"Kotnis, Bhushan","roleDisplay":"VerfasserIn","role":"aut","family":"Kotnis","given":"Bhushan"},{"given":"Vivi","family":"Nastase","role":"aut","roleDisplay":"VerfasserIn","display":"Nastase, Vivi"}],"language":["eng"],"recId":"1675677042","type":{"bibl":"chapter","media":"Online-Ressource"},"note":["Gesehen am 02.09.2019"],"id":{"eki":["1675677042"]},"origin":[{"dateIssuedKey":"2018","dateIssuedDisp":"2 Mar 2018"}],"name":{"displayForm":["Bhushan Kotnis and Vivi Nastase"]},"relHost":[{"part":{"year":"2018","text":"(2018)","extent":"6"},"titleAlt":[{"title":"Arxiv.org"},{"title":"Arxiv.org e-print archive"},{"title":"Arxiv e-print archive"},{"title":"De.arxiv.org"}],"pubHistory":["1991 -"],"language":["eng"],"recId":"509006531","note":["Gesehen am 28.05.2024"],"disp":"Learning knowledge graph embeddings with type regularizerArxiv","type":{"media":"Online-Ressource","bibl":"edited-book"},"title":[{"title":"Arxiv","title_sort":"Arxiv"}],"physDesc":[{"extent":"Online-Ressource"}],"id":{"eki":["509006531"],"zdb":["2225896-6"]},"origin":[{"publisher":"Cornell University ; Arxiv.org","dateIssuedKey":"1991","dateIssuedDisp":"1991-","publisherPlace":"Ithaca, NY ; [Erscheinungsort nicht ermittelbar]"}]}],"physDesc":[{"extent":"6 S."}]} | ||
| SRT | |a KOTNISBHUSLEARNINGKN2201 | ||