Forest Reranking through Subtree Ranking
نویسندگان
چکیده
We propose the subtree ranking approach to parse forest reranking which is a generalization of current perceptron-based reranking methods. For the training of the reranker, we extract competing local subtrees, hence the training instances (candidate subtree sets) are very similar to those used during beamsearch parsing. This leads to better parameter optimization. Another chief advantage of the framework is that arbitrary learning to rank methods can be applied. We evaluated our reranking approach on German and English phrase structure parsing tasks and compared it to various state-of-the-art reranking approaches such as the perceptron-based forest reranker. The subtree ranking approach with a Maximum Entropy model significantly outperformed the other approaches.
منابع مشابه
A Reranking Approach for Dependency Parsing with Variable-sized Subtree Features
Employing higher-order subtree structures in graph-based dependency parsing has shown substantial improvement over the accuracy, however suffers from the inefficiency increasing with the order of subtrees. We present a new reranking approach for dependency parsing that can utilize complex subtree representation by applying efficient subtree selection heuristics. We demonstrate the effectiveness...
متن کاملA Reranking Model for Discourse Segmentation using Subtree Features
This paper presents a discriminative reranking model for the discourse segmentation task, the first step in a discourse parsing system. Our model exploits subtree features to rerank Nbest outputs of a base segmenter, which uses syntactic and lexical features in a CRF framework. Experimental results on the RST Discourse Treebank corpus show that our model outperforms existing discourse segmenter...
متن کاملSubmodular Reranking with Multiple Feature Modalities for Image Retrieval
We propose a submodular reranking algorithm to boost image retrieval performance based on multiple ranked lists obtained from multiple modalities in an unsupervised manner. We formulate the reranking problem as maximizing a submodular and non-decreasing objective function that consists of an information gain term and a relative ranking consistency term. The information gain term exploits relati...
متن کاملRank canonical correlation analysis and its application in visual search reranking
Ranking relevance degree information is widely utilized in the ranking models of information retrieval applications, such as text and multimedia retrieval, question answering, and visual search reranking. However, existing feature dimensionality reduction methods neglect this kind of valuable potential supervised information. In this paper, we extend the pairwise constraints from the traditiona...
متن کاملThird-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 کامل