Experiments and evaluation | Figure 1 gives the results of the reranked thesaurus for these entries in terms of R-precision and MAP against reference W5 for various values of G. Although the level of these measures does not change a lot for G > 5, the graph of Figure 1 shows that G = 15 appears to be an optimal value. |
Experiments and evaluation | 4.3 Evaluation of the reranked thesaurus |
Experiments and evaluation | Table 4 gives the evaluation of the application of our reranking method to the initial thesaurus according to the same principles as in section 4.1. |
Improving a distributional thesaurus | o reranking of entry’s neighbors according to bad neighbors. |
Improving a distributional thesaurus | As mentioned in section 3.1, the starting point of our reranking process is the definition of a model for determining to what extent a word in a sentence, which is not supposed to be known in the context of this task, corresponds or not to a reference word E. This task can also be viewed as a tagging task in which the occurrences of a target word T are labeled with two tags: E and notE. |
Improving a distributional thesaurus | 3.4 Identification of bad neighbors and thesaurus reranking |
Abstract | We adapt discriminative reranking to improve the performance of grounded language acquisition, specifically the task of learning to follow navigation instructions from observation. |
Abstract | Unlike conventional reranking used in syntactic and semantic parsing, gold-standard reference trees are not naturally available in a grounded setting. |
Background | The baseline generative model we use for reranking employs the unsupervised PCFG induction approach introduced by Kim and Mooney (2012). |
Introduction | Since their system employs a generative model, discriminative reranking (Collins, 2000) could p0-tentially improve its performance. |
Introduction | By training a discriminative classifier that uses global features of complete parses to identify correct interpretations, a reranker can significantly improve the accuracy of a generative model. |
Introduction | Reranking has been successfully employed to improve syntactic parsing (Collins, 2002b), semantic parsing (Lu et al., 2008; Ge and Mooney, 2006), semantic role labeling (Toutanova et al., 2005), and named entity recognition (Collins, 2002c). |
Abstract | To do so we follow an n-best list reranking approach that exploits recent advances in learning to rank techniques. |
Discriminative Reranking for OCR | 2.2 Ensemble reranking |
Discriminative Reranking for OCR | In addition to the above mentioned approaches, we couple simple feature selection and reranking models combination via a straightforward ensemble learning method similar to stacked generalization (Wolpert, 1992) and Combiner (Chan and Stolfo, 1993). |
Discriminative Reranking for OCR | These features are used by the baseline system5 as well as by the various reranking methods. |
Experiments | Table 2 presents the WER for our baseline hypothesis, the best hypothesis in the list (our oracle) and our best reranking results which we describe in details in §3.2. |
Experiments | on the reranking performance for one of our best reranking models, namely RankSVM. |
Experiments | 3.2 Reranking results |
Introduction | A straightforward alternative which we advocate in this paper is to use the available information to rerank the hypotheses in the n-best lists. |
Introduction | Discriminative reranking allows each hypothesis to be represented as an arbitrary set of features without the need to explicitly model their interactions. |
Introduction | We describe our features and reranking approach in §2, and we present our experiments and results in §3. |
Introduction | Therefore, we use hypergraph reranking (Huang and Chiang, 2007; Huang, 2008), which proves to be effective for integrating nonlocal features into dynamic programming, to alleviate this problem. |
Introduction | 3 In the second pass, we use the hypergraph reranking algorithm (Huang, 2008) to find promising translations using additional dependency features (i.e., features 8-10 in the list). |
Introduction | Table 3 shows the effect of hypergraph reranking . |
Introduction | In the reranking framework: in principle, all |
Introduction | the models in previous category can be used in the reranking framework, because in the reranking we have all the information (source and target words/phrases, alignment) about the translation process. |
Introduction | One disadvantage of carrying out reordering in reranking is the representativeness of the N-best list is often a question mark. |