Abstract | ||
---|---|---|
This paper deals with the extraction of semantic relations from scientific texts. Pattern-based representations are compared to word embeddings in unsupervised clustering experiments, according to their potential to discover new types of semantic relations and recognize their instances. The results indicate that sequential pattern mining can significantly improve pattern-based representations, even in a completely unsupervised setting. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1007/978-3-319-46349-0_21 | ADVANCES IN INTELLIGENT DATA ANALYSIS XV |
Field | DocType | Volume |
Parse tree,Pattern recognition,Computer science,Semantic relation,Artificial intelligence,Cluster analysis,Sequential Pattern Mining,Relationship extraction | Conference | 9897 |
ISSN | Citations | PageRank |
0302-9743 | 2 | 0.38 |
References | Authors | |
28 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kata Gábor | 1 | 12 | 4.13 |
Haïfa Zargayouna | 2 | 76 | 11.85 |
isabelle tellier | 3 | 84 | 20.31 |
Davide Buscaldi | 4 | 436 | 54.12 |
thierry charnois | 5 | 98 | 17.21 |