0.25
0.5
0.75
1.25
1.5
1.75
2
Learning a Cross-Lingual Semantic Representation of Relations Expressed in Text
Published on Jul 15, 20151939 Views
Learning cross-lingual semantic representations of relations from textual data is useful for tasks like cross-lingual information retrieval and question answering. So far, research has been mainly f
Related categories
Chapter list
Learning a Cross-Lingual Semantic Representation of Relations Expressed in Text00:00
Cross-lingual Entity Linking 00:23
Cross-lingual Relation Linking 01:20
Entity vs. Relation Linking 03:16
Representations of Entities vs. Relations 05:39
Cross-lingual Relation Clustering and Grounding - Pipeline07:55
Cross Lingual Semantic Representation 08:56
Dependency Parsing vs Semantic Parsing09:02
Multi-lingual SRL Graphs10:26
Cross-lingual Meaning Representation11:43
Clustering Cross-lingual SRL Graphs12:45
Similarity Metrics for SRL Graphs 12:56
Similarity Matrix 14:05
Resulting Similarity Matrix15:21
Result of Spectral Clustering16:16
Linking Graph Clusters17:30
Linking Predicate Clusters to DBpedia Properties17:36
Evaluation Qald18:36
QALD Challenge 18:43
Baselines19:26
Results: Baseline Performance20:24
Results: Effect of diversity of data21:42
Results: Effect of # of eigenvectors 23:01
Summary23:37
Cross-lingual Semantic Clusters of Relations23:39
Thank you!23:45