1 |
"Wikily" Supervised Neural Translation Tailored to Cross-Lingual Tasks ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Wikily Supervised Neural Translation Tailored to Cross-Lingual Tasks ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
ParsiNLU: A Suite of Language Understanding Challenges for Persian ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Mutlitask Learning for Cross-Lingual Transfer of Semantic Dependencies ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Cross-Lingual Transfer of Natural Language Processing Systems
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Cross-Lingual Transfer of Semantic Roles: From Raw Text to Semantic Roles ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Cross-Lingual Syntactic Transfer with Limited Resources ...
|
|
|
|
Abstract:
We describe a simple but effective method for cross-lingual syntactic transfer of dependency parsers, in the scenario where a large amount of translation data is not available. The method makes use of three steps: 1) a method for deriving cross-lingual word clusters, which can then be used in a multilingual parser; 2) a method for transferring lexical information from a target language to source language treebanks; 3) a method for integrating these steps with the density-driven annotation projection method of Rasooli and Collins (2015). Experiments show improvements over the state-of-the-art in several languages used in previous work, in a setting where the only source of translation data is the Bible, a considerably smaller corpus than the Europarl corpus used in previous work. Results using the Europarl corpus as a source of translation data show additional improvements over the results of Rasooli and Collins (2015). We conclude with results on 38 datasets from the Universal Dependencies corpora. ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://dx.doi.org/10.48550/arxiv.1610.06227 https://arxiv.org/abs/1610.06227
|
|
BASE
|
|
Hide details
|
|
|
|