Abstract | ||
---|---|---|
Multiword Expressions (MWEs) display some kind of linguistic and statistical markedness that may influence the effectiveness of techniques that automatically identify them in texts. While parsing-based techniques for MWE identification are considered to be better at handling long-distance dependencies, passivization and internal modification, statistics-based techniques use association measures to detect statistical markedness regardless of syntactic form. In this paper we compare these two approaches focusing on nominal compounds in Portuguese. We compare the accuracy of each method and propose that combining the strengths of both for increased accuracy. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1007/978-3-319-41552-9_23 | COMPUTATIONAL PROCESSING OF THE PORTUGUESE LANGUAGE (PROPOR 2016) |
Field | DocType | Volume |
Markedness,Expression (mathematics),Computer science,Portuguese,Artificial intelligence,Natural language processing,Parsing,Syntax,Multiword expression | Conference | 9727 |
ISSN | Citations | PageRank |
0302-9743 | 0 | 0.34 |
References | Authors | |
7 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Leonardo Zilio | 1 | 8 | 8.69 |
Rodrigo Wilkens | 2 | 5 | 7.61 |
Luís Möllmann | 3 | 0 | 0.34 |
eric wehrli | 4 | 29 | 6.20 |
Silvio Cordeiro | 5 | 7 | 2.44 |
Aline Villavicencio | 6 | 286 | 35.24 |