Experiments | The dependency parser and POS tagger are trained on supervised data and up-trained on data labeled by the CKY—style bottom-up constituent parser of Huang et al. |
Experiments | Therefore, we could not use the constituent parser for ASR rescoring since utterances can be very long, although the shorter up-training text data was not a problem.7 We evaluate both unlabeled (UAS) and labeled dependency accuracy (LAS). |
Experiments | Figure 3 shows improvements to parser accuracy through up-training for different amount of (randomly selected) data, where the last column indicates constituent parser score (91.4% UAS). |
Incorporating Syntactic Structures | 4We note that while we have demonstrated substructure sharing for dependency parsing, the same improvements can be made to a shift—reduce constituent parser (Sagae and Lavie, 2006). |
Up-Training | (2010) used up-training as a domain adaptation technique: a constituent parser —which is more robust to domain changes — was used to label a new domain, and a fast dependency parser |
Up-Training | We parse a large corpus of text with a very accurate but very slow constituent parser and use the resulting data to up-train our tools. |
Abstract | This paper presents a higher-order model for constituent parsing aimed at utilizing more local structural context to decide the score of a grammar rule instance in a parse tree. |
Conclusion | This paper has presented a higher-order model for constituent parsing that factorizes a parse tree into larger parts than before, in hopes of increasing its power of discriminating the true parse from the others without losing tractability. |
Conclusion | More importantly, it extends the existing works into a more general framework of constituent parsing to utilize more lexical and structural context and incorporate more strength of various parsing techniques. |
Conclusion | However, higher-order constituent parsing inevitably leads to a high computational complexity. |
Introduction | Similarly, we can define the order of constituent parsing in terms of the number of grammar rules in a part. |
Introduction | Then, the previous discriminative constituent parsing models (Johnson, 2001; Henderson, 2004; Taskar et al., 2004; Petrov and Klein, 2008a; |
Introduction | The discriminative re-scoring models (Collins, 2000; Collins and Duffy, 2002; Charniak and Johnson, 2005; Huang, 2008) can be viewed as previous attempts to higher-order constituent parsing , using some parts containing more than one grammar rule as nonlocal features. |
Scoring a Sentence | For machine translation, a model that builds target-side constituency parses , such as that of Galley et a1. |
Tree Transformations | number of transformations of Treebank constituency parses that allow us to capture such dependencies. |
Treelet Language Modeling | There is one additional hurdle in the estimation of our model: while there exist corpora with human-annotated constituency parses like the Penn Treebank (Marcus et al., 1993), these corpora are quite small — on the order of millions of tokens — and we cannot gather nearly as many counts as we can for 77.-grams, for which billions or even trillions (Brants et al., 2007) of tokens are available on the Web. |
Treelet Language Modeling | However, we can use one of several high-quality constituency parsers (Collins, 1997; Charniak, 2000; Petrov et al., 2006) to automatically generate parses. |
Abstract | This paper evaluates two empirical strategies to integrate multiword units in a real constituency parsing context and shows that the results are not as promising as has sometimes been suggested. |
Introduction | view, their incorporation has also been considered such as in (Nivre and Nilsson, 2004) for dependency parsing and in (Arun and Keller, 2005) in constituency parsing . |
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. |
Method | HILDA’s features: We incorporate the original features used in the HILDA discourse parser with slight modification, which include the following four types of features occurring in SL, SR, or both: (1) N-gram prefixes and suffixes; (2) syntactic tag prefixes and suffixes; (3) lexical heads in the constituent parse tree; and (4) PCS tag of the dominating nodes. |
Related work | (2009) attempted to recognize implicit discourse relations (discourse relations which are not signaled by explicit connectives) in PDTB by using four classes of features — contextual features, constituent parse features, dependency parse features, and lexical features — and explored their individual influence on performance. |
Related work | They showed that the production rules extracted from constituent parse trees are the most effective features, while contextual features are the weakest. |
Experiments and Analysis | (2009) use the maximum entropy inspired generative parser (GP) of Charniak (2000) as their constituent parser . |
Related Work | They automatically convert the dependency—structure CDT into the phrase—structure style of CTBS using a statistical constituency parser trained on CTBS. |
Related Work | Their experiments show that the combined treebank can significantly improve the performance of constituency parsers . |
Abstract | Syntagmatic lexical relations are implicitly captured by constituent parsing and are utilized via system combination. |
Capturing Syntagmatic Relations via Constituency Parsing | The majority of the state-of-the-art constituent parsers are based on generative PCFG learning, with lexicalized (Collins, 2003; Chamiak, 2000) or latent annotation (PCFG-LA) (Matsuzaki et al., 2005; Petrov et al., 2006; Petrov and Klein, 2007) refinements. |
State-of-the-Art | Xu, 2011), POS tagging (Huang et al., 2007, 2009), constituency parsing (Zhang and Clark, 2009; Wang et al., 2006) and dependency parsing (Zhang and Clark, 2008; Huang and Sagae, 2010; Li et al., 2011). |