Papers by Vinicius Woloszyn
An Empirical Comparison of Question Classification Methods for Question Answering Systems (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing methods for Question Classification are monolingual, but they are not suitable for low-resourced languages. |
| Approach: | They propose to classify the most recent methods in four different categories . they propose to use a low, medium, high, and very high level of dependency on external resources . |
| Outcome: | The proposed method outperforms methods not suitable for low-resource languages. |
BlogSet-BR: A Brazilian Portuguese Blog Corpus (L18-1)
Copied to clipboard
| Challenge: | Several efforts have been made to build a corpus based on user-generated content . however, there is still a lack of a large semi-structured corpus that also contains author profiles in Brazilian Portuguese. |
| Approach: | They propose to build a Brazilian Portuguese corpus with 2.1 billion words extracted from 7.4 million posts over 808 thousand different Brazilian blogs. |
| Outcome: | The proposed corpus contains 2.1 billion words extracted from 7.4 million posts over 808 thousand different Brazilian blogs. |