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.

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).

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).

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).

(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

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.

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.

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.

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.

However, higher-order constituent parsing inevitably leads to a high computational complexity.

Similarly, we can define the order of constituent parsing in terms of the number of grammar rules in a part.

Then, the previous discriminative constituent parsing models (Johnson, 2001; Henderson, 2004; Taskar et al., 2004; Petrov and Klein, 2008a;

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.

For machine translation, a model that builds target-side constituency parses , such as that of Galley et a1.

number of transformations of Treebank constituency parses that allow us to capture such dependencies.

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.

However, we can use one of several high-quality constituency parsers (Collins, 1997; Charniak, 2000; Petrov et al., 2006) to automatically generate parses.

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.

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 .

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.

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.

(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.

They showed that the production rules extracted from constituent parse trees are the most effective features, while contextual features are the weakest.

(2009) use the maximum entropy inspired generative parser (GP) of Charniak (2000) as their constituent parser .

They automatically convert the dependency—structure CDT into the phrase—structure style of CTBS using a statistical constituency parser trained on CTBS.

Their experiments show that the combined treebank can significantly improve the performance of constituency parsers .

Syntagmatic lexical relations are implicitly captured by constituent parsing and are utilized via system combination.

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.

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).