Name
Abstract | ||
|---|---|---|
Most successful Entity Linking (EL) methods aim to link mentions to their referent entities in a structured Knowledge Base (KB) by comparing their respective contexts, often using similarity measures. While the KB structure is given, current methods have suffered from impoverished information representations on the mention side. In this paper, we demonstrate the effectiveness of Abstract Meaning Representation (AMR) (Banarescu et al., 2013) to select high quality sets of entity “collaborators” to feed a simple similarity measure (Jaccard) to link entity mentions. Experimental results show that AMR captures contextual properties discriminative enough to make linking decisions, without the need for EL training data, and that system with AMR parsing output outperforms hand labeled traditional semantic roles as context representation for EL. Finally, we show promising preliminary results for using AMR to select sets of “coherent” entity mentions for collective entity linking 1 . |
Year | Venue | Field |
|---|---|---|
2015 | HLT-NAACL | Entity linking,Similarity measure,Computer science,Weak entity,Jaccard index,Natural language processing,Artificial intelligence,Knowledge base,Parsing,Discriminative model,Machine learning,Semantic role labeling |
DocType | Citations | PageRank |
Conference | 28 | 0.92 |
References | Authors | |
18 | 5 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Xiaoman Pan | 1 | 53 | 8.65 |
| Taylor Cassidy | 2 | 187 | 12.48 |
| Ulf Hermjakob | 3 | 684 | 76.21 |
| Heng Ji | 4 | 1544 | 127.27 |
| Kevin Knight | 5 | 5096 | 462.44 |