Abstract | Secondly, integrating multiword expressions in the parser grammar followed by a reranker specific to such expressions slightly improves all evaluation metrics. |
Introduction | Our proposal is to evaluate two discriminative strategies in a real constituency parsing context: (a) pre-grouping MWE before parsing; this would be done with a state-of-the-art recognizer based on Conditional Random Fields; (b) parsing with a grammar including MWE identification and then reranking the output parses thanks to a Maximum Entropy model integrating MWE-dedicated features. |
MWE-dedicated Features | In order to make these models comparable, we use two comparable sets of feature templates: one adapted to sequence labelling (CRF—based MWER) and the other one adapted to reranking (MaXEnt-based reranker ). |
MWE-dedicated Features | The reranker templates are instantiated only for the nodes of the candidate parse tree, which are leaves dominated by a MWE node (i.e. |
MWE-dedicated Features | o RERANKER : for each leaf (in position 77.) |
Two strategies, two discriminative models | 3.2 Reranking |
Two strategies, two discriminative models | Discriminative reranking consists in reranking the n-best parses of a baseline parser with a discriminative model, hence integrating features associated with each node of the candidate parses. |
Two strategies, two discriminative models | Formally, given a sentence 8, the reranker selects the best candidate parse p among a set of candidates P (s) with respect to a scoring function V9: |
Abstract | The hypergraph structure encodes exponentially many derivations, which we rerank discriminatively using local and global features. |
Introduction | ia Discriminative Reranking |
Introduction | The performance of this baseline system could be potentially further improved using discriminative reranking (Collins, 2000). |
Introduction | Typically, this method first creates a list of n-best candidates from a generative model, and then reranks them with arbitrary features (both local and global) that are either not computable or intractable to compute within the |
Problem Formulation | The hypergraph representation allows us to decompose the feature functions and compute them piecemeal at each hyperarc (or sub-derivation), rather than at the root node as in conventional n-best list reranking . |
Related Work | Discriminative reranking has been employed in many NLP tasks such as syntactic parsing (Char-niak and Johnson, 2005; Huang, 2008), machine translation (Shen et al., 2004; Li and Khudanpur, 2009) and semantic parsing (Ge and Mooney, 2006). |
Related Work | Our model is closest to Huang (2008) who also performs forest reranking on a hypergraph, using both local and nonlocal features, whose weights are tuned with the averaged perceptron algorithm (Collins, 2002). |
Related Work | We adapt forest reranking to generation and introduce several task-specific features that boost performance. |
Abstract | Our SR-TSG parser achieves an F 1 score of 92.4% in the Wall Street Journal (WSJ) English Penn Treebank parsing task, which is a 7.7 point improvement over a conventional Bayesian TSG parser, and better than state-of-the-art discriminative reranking parsers. |
Experiment | It should be noted that discriminative reranking parsers such as (Char-niak and Johnson, 2005) and (Huang, 2008) are constructed on a generative parser. |
Experiment | The reranking parser takes the k-best lists of candidate trees or a packed forest produced by a baseline parser (usually a generative model), and then reranks the candidates using arbitrary features. |
Experiment | Hence, we can expect that combining our SR-TSG model with a discriminative reranking parser would provide better performance than SR-TSG alone. |
Introduction | Our SR-TSG parser achieves an F1 score of 92.4% in the WSJ English Penn Treebank parsing task, which is a 7.7 point improvement over a conventional Bayesian TSG parser, and superior to state-of-the-art discriminative reranking parsers. |
Experiments | We report machine translation reranking results in Section 5.4. |
Experiments | The latter report results for two binary classifiers: RERANK uses the reranking features of Charniak and Johnson (2005), and TSG uses |
Experiments | All generative models improve, but TREELET-RULE remains the best, now outperforming the RERANK system, though of course it is likely that RERANK would improve if it could be scaled up to more training data. |
Introduction | We also show fluency improvements in a preliminary machine translation reranking experiment. |