Generative Constituent Parsing and Discriminative Dependency Reranking: Experiments on English and French
نویسندگان
چکیده
We present an architecture for parsing in two steps. A phrase-structure parser builds for each sentence an n-best list of analyses which are converted to dependency trees. These dependency structures are then rescored by a discriminative reranker. Our method is language agnostic and enables the incorporation of additional information which are useful for the choice of the best parse candidate. We test our approach on the the Penn Treebank and the French Treebank. Evaluation shows a significative improvement on different parse metrics.
منابع مشابه
Third-order Variational Reranking on Packed-Shared Dependency Forests
We propose a novel forest reranking algorithm for discriminative dependency parsing based on a variant of Eisner’s generative model. In our framework, we define two kinds of generative model for reranking. One is learned from training data offline and the other from a forest generated by a baseline parser on the fly. The final prediction in the reranking stage is performed using linear interpol...
متن کاملCombine Constituent and Dependency Parsing via Reranking
This paper presents a reranking approach to combining constituent and dependency parsing, aimed at improving parsing performance on both sides. Most previous combination methods rely on complicated joint decoding to integrate graphand transition-based dependency models. Instead, our approach makes use of a high-performance probabilistic context free grammar (PCFG) model to output k-best candida...
متن کاملEfficient Stacked Dependency Parsing by Forest Reranking
This paper proposes a discriminative forest reranking algorithm for dependency parsing that can be seen as a form of efficient stacked parsing. A dynamic programming shift-reduce parser produces a packed derivation forest which is then scored by a discriminative reranker, using the 1-best tree output by the shift-reduce parser as guide features in addition to third-order graph-based features. T...
متن کاملA generative re-ranking model for dependency parsing
We propose a framework for dependency parsing based on a combination of discriminative and generative models. We use a discriminative model to obtain a kbest list of candidate parses, and subsequently rerank those candidates using a generative model. We show how this approach allows us to evaluate a variety of generative models, without needing different parser implementations. Moreover, we pre...
متن کاملFeatures for Phrase-Structure Reranking from Dependency Parses
Radically different approaches have been proved to be effective for phrase-structure and dependency parsers in the last decade. Here, we aim to exploit the divergence in these approaches and show the utility of features extracted from the automatic dependency parses of sentences for a discriminative phrase-structure parser. Our experiments show a significant improvement over the state-of-the-ar...
متن کامل