598–603), Providence, Rhode Island, USA.Ĭharniak, E. In Proceedings of the national conference on artificial intelligence (pp. Statistical parsing with a context-free grammar and word statistics. In Proceedings of the workshop on computational environments for grammar development and linguistic engineering (pp. A tool for supervised training of parsed corpora. In Proceedings of the international conference recent advances in natural language processing (pp. Confidence measures for stochastic parsing. Estimation of stochastic context-free grammars and their use as language models. The Journal of the Acoustical Society of America, 65, 31–35.īenedí, J. M., & Sánchez, J. A. Trainable grammars for speech recognition. This process is experimental and the keywords may be updated as the learning algorithm improves.īaker, J. K. These keywords were added by machine and not by the authors. Confidence Measures can be efficiently computed in the IP framework and can help in detecting erroneous constituents within the IP process more quickly, as they provide discriminant information over all the IP process. The use of Confidence Measures in IP is also presented as an efficient technique to detect erroneous parse trees. In addition, this order also introduces computational advantages into the lookout of most probable tree for interactive bottom-up parsing algorithms. 9.4, a left-to-right depth-first tree review order will be introduced. However, in order to efficiently calculate the next best tree in IP framework, in Sect. Specifically, the IP protocol will be of desultory order that is, in IP the user can edit any part of the parse tree and in any order. In principle, the interaction protocol defined in the IP framework differs from the left-to-right interaction protocol used throughout this book. These interactive systems can help to human annotators in creating error-free parse trees with little effort, when compared with manual post-editing of the trees provided by an automatic parser. This formal framework allows us to make the construction of interactive systems for tree annotation. This chapter introduces the Interactive Parsing (IP) framework for obtaining the correct syntactic parse tree of a given sentence.
0 Comments
Leave a Reply. |