Thema4979: Unterschied zwischen den Versionen
Ck1908 (Diskussion | Beiträge) |
Ck1908 (Diskussion | Beiträge) |
||
| (2 dazwischenliegende Versionen desselben Benutzers werden nicht angezeigt) | |||
| Zeile 5: | Zeile 5: | ||
|Abschlussarbeitstyp=Master | |Abschlussarbeitstyp=Master | ||
|Betreuer=Mary Ann Tan; Russa Biswas; Harald Sack | |Betreuer=Mary Ann Tan; Russa Biswas; Harald Sack | ||
| − | |||
|Forschungsgruppe=Information Service Engineering | |Forschungsgruppe=Information Service Engineering | ||
|Abschlussarbeitsstatus=Offen | |Abschlussarbeitsstatus=Offen | ||
| Zeile 11: | Zeile 10: | ||
|Ausschreibung=Master_Thesis_EA_DDB.pdf | |Ausschreibung=Master_Thesis_EA_DDB.pdf | ||
|Beschreibung DE=A Knowledge Graph (KG) contains real-world information organized to enable data sharing, understanding and reasoning. In order to make a KG consistent, integration with existing KGs is required. One such task, Entity Alignment1 (EA), attempts to map equivalent entities from one KG (source) to another KG (target). | |Beschreibung DE=A Knowledge Graph (KG) contains real-world information organized to enable data sharing, understanding and reasoning. In order to make a KG consistent, integration with existing KGs is required. One such task, Entity Alignment1 (EA), attempts to map equivalent entities from one KG (source) to another KG (target). | ||
| − | + | </br> | |
| + | </br> | ||
EA techniques are often hampered by entity name variations, multilingualism, and the heterogeneity of source-target KGs. Recent developments in Machine Learning and Natural Language Processing have been shown to mitigate these challenges. | EA techniques are often hampered by entity name variations, multilingualism, and the heterogeneity of source-target KGs. Recent developments in Machine Learning and Natural Language Processing have been shown to mitigate these challenges. | ||
| − | + | </br> | |
| + | </br> | ||
In particular, KG Embeddings3 (KGEs) have proven invaluable through their ability to encode an entity’s graph substructure, describing its neighborhood and the relations attached to it. These dense representations enable similarity-based scoring functions to compute equivalence between entities. | In particular, KG Embeddings3 (KGEs) have proven invaluable through their ability to encode an entity’s graph substructure, describing its neighborhood and the relations attached to it. These dense representations enable similarity-based scoring functions to compute equivalence between entities. | ||
| − | + | </br> | |
| + | </br> | ||
In addition, pre-trained Language Models4 (PLMs) encode the semantics found in the literals attached to entity names and attributes. They have been shown to address name variations and multilingualism. | In addition, pre-trained Language Models4 (PLMs) encode the semantics found in the literals attached to entity names and attributes. They have been shown to address name variations and multilingualism. | ||
| − | + | </br> | |
| + | </br> | ||
The goal of this thesis is to explore and combine the aforementioned techniques in order to integrate the German Digital Library4 Knowledge Graph (DDB-KG) to existing and well-established KGs, such as, the Integrated Authority File (GND) and Wikidata. | The goal of this thesis is to explore and combine the aforementioned techniques in order to integrate the German Digital Library4 Knowledge Graph (DDB-KG) to existing and well-established KGs, such as, the Integrated Authority File (GND) and Wikidata. | ||
| − | + | </br> | |
| − | Prerequisites: | + | </br> |
| − | - Good programming skills in Python | + | <strong>Prerequisites:</strong> |
| − | - Interest in Cultural Heritage | + | </br>- Good programming skills in Python |
| − | - Interest in Natural Language Processing | + | </br>- Interest in Cultural Heritage |
| − | - Interest in Machine Learning approaches | + | </br>- Interest in Natural Language Processing |
| − | Interest in Semantic Web technologies | + | </br>- Interest in Machine Learning approaches |
| + | </br>- Interest in Semantic Web technologies | ||
}} | }} | ||
Aktuelle Version vom 1. Dezember 2022, 09:58 Uhr
Abschlussarbeitstyp: Master
Betreuer: Mary Ann Tan, Russa Biswas, Harald Sack
Forschungsgruppe: Information Service Engineering
Archivierungsnummer: 4979
Abschlussarbeitsstatus: Offen
Beginn:
02. Januar 2022
Abgabe: unbekannt
A Knowledge Graph (KG) contains real-world information organized to enable data sharing, understanding and reasoning. In order to make a KG consistent, integration with existing KGs is required. One such task, Entity Alignment1 (EA), attempts to map equivalent entities from one KG (source) to another KG (target).
EA techniques are often hampered by entity name variations, multilingualism, and the heterogeneity of source-target KGs. Recent developments in Machine Learning and Natural Language Processing have been shown to mitigate these challenges.
In particular, KG Embeddings3 (KGEs) have proven invaluable through their ability to encode an entity’s graph substructure, describing its neighborhood and the relations attached to it. These dense representations enable similarity-based scoring functions to compute equivalence between entities.
In addition, pre-trained Language Models4 (PLMs) encode the semantics found in the literals attached to entity names and attributes. They have been shown to address name variations and multilingualism.
The goal of this thesis is to explore and combine the aforementioned techniques in order to integrate the German Digital Library4 Knowledge Graph (DDB-KG) to existing and well-established KGs, such as, the Integrated Authority File (GND) and Wikidata.
Prerequisites:
- Good programming skills in Python
- Interest in Cultural Heritage
- Interest in Natural Language Processing
- Interest in Machine Learning approaches
- Interest in Semantic Web technologies
Ausschreibung: Download (pdf)