Дискурстық Тәуелді Парсинг

AbstractOne of the main bottlenecks in developing discourse dependency parsers is the lack of annotated training data. A potential solution is to utilize abundant unlabeled data by using unsupervised techniques, …...

AbstractIn recent years, top-down neural models have achieved significant success in text-level discourse parsing. Nevertheless, they still suffer from the top-down error propagation issue, especially when the performance on the …...