Abstract | Experiments show that web-scale data improves statistical dependency parsing, particularly for long dependency relationships . |
Conclusion | The results show that web-scale data improves the dependency parsing, particularly for long dependency relationships . |
Experiments | The results here show that the proposed approach improves the dependency parsing performance, particularly for long dependency relationships . |
Introduction | The results show that web-derived selectional preference can improve the statistical dependency parsing, particularly for long dependency relationships . |
Related Work | Our research, however, applies the web-scale data (Google hits and Google V1) to model the word-to-word dependency relationships rather than compound bracketing disambiguation. |
Related Work | Our approach, however, extends these techniques to dependency parsing, particularly for long dependency relationships , which involves more challenging tasks than the previous work. |
Introduction | We also used the Kyoto University Text Corpus4 that provides dependency relations information for the same articles as the NAIST Text Corpus. |
Introduction | To create a subject detection model for Italian, we used the TUT corpus9 (Bosco et al., 2010), which contains manually annotated dependency relations and their labels, consisting of 80,878 tokens in CoNLL format. |
Introduction | We induced an maximum entropy classifier by using as items all arcs of dependency relations , each of which is used as a positive instance if its label is subject; otherwise it is used as a negative instance. |