Parsing and MWE Detection: Fips at the PARSEME Shared Task
| Autor: | Eric Wehrli, Vasiliki Foufi, Luka Nerima |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Machine translation
Computer science Speech recognition Collocation identification computer.software_genre ddc:616.0757 Task (project management) ddc:410 ddc:025.063 Fips Verbal multiword expressions Collocation Parsing business.industry Parser Deep parser Identification (information) VMWE identification VMWE PARSEME shared task Artificial intelligence business computer Natural language processing Sentence |
| Zdroj: | Proceedings of the 13th Workshop on Multiword Expressions (MWE 2017) Proceedings of the 13th Workshop on Multiword Expressions (MWE 2017) pp. 54-59 |
| DOI: | 10.18653/v1/w17-1706 |
| Popis: | Identifying multiword expressions (MWEs) in a sentence in order to ensure their proper processing in subsequent applications, like machine translation, and performing the syntactic analysis of the sentence are interrelated processes. In our approach, priority is given to parsing alternatives involving collocations, and hence collocational information helps the parser through the maze of alternatives, with the aim to lead to substantial improvements in the performance of both tasks (collocation identification and parsing), and in that of a subsequent task (machine translation). In this paper, we are going to present our system and the procedure that we have followed in order to participate to the open track of the PARSEME shared task on automatic identification of verbal multiword expressions (VMWEs) in running texts. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|