Search Results for author:
Found 2 papers, 1 papers with code
Zero-shot cross-lingual identification of direct speech using distant supervision
Crucially, by training the classifier with the quotation marks removed, it was forced to learn the linguistic characteristics of direct speech rather than the typography of quotation marks.
Evaluation of really good grammatical error correction
We find that GPT-3 in a few-shot setting by far outperforms previous grammatical error correction systems for Swedish, a language comprising only 0. 11% of its training data.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
