jurafsky&martin_3rdEd_17 (1).pdf

Other aspects of the tree such as the lexical

Info icon This preview shows pages 224–227. Sign up to view the full content.

View Full Document Right Arrow Icon
other aspects of the tree such as the lexical identity (the lexeme that is likely to be a complementizer, as a subordinating conjunction). Node-splitting is not without problems; it increases the size of the grammar and hence reduces the amount of training data available for each grammar rule, leading to overfitting. Thus, it is important to split to just the correct level of granularity for a particular training set. While early models employed hand-written rules to try to find an optimal number of non-terminals (Klein and Manning, 2003b) , modern models
Image of page 224

Info icon This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
13.6 P ROBABILISTIC L EXICALIZED CFG S 225 automatically search for the optimal splits. The split and merge algorithm of Petrov Split and merge et al. (2006) , for example, starts with a simple X-bar grammar, alternately splits the non-terminals, and merges non-terminals, finding the set of annotated nodes that maximizes the likelihood of the training set treebank. As of the time of this writing, the performance of the Petrov et al. (2006) algorithm was the best of any known parsing algorithm on the Penn Treebank. 13.6 Probabilistic Lexicalized CFGs The previous section showed that a simple probabilistic CKY algorithm for pars- ing raw PCFGs can achieve extremely high parsing accuracy if the grammar rule symbols are redesigned by automatic splits and merges. In this section, we discuss an alternative family of models in which instead of modifying the grammar rules, we modify the probabilistic model of the parser to allow for lexicalized rules. The resulting family of lexicalized parsers includes the well-known Collins parser (Collins, 1999) and Charniak parser (Charniak, 1997) , Collins parser Charniak parser both of which are publicly available and widely used throughout natural language processing. We saw in Section 11.4.3 that syntactic constituents could be associated with a lexical head , and we defined a lexicalized grammar in which each non-terminal Lexicalized grammar in the tree is annotated with its lexical head, where a rule like VP ! VBD NP PP would be extended as VP(dumped) ! VBD(dumped) NP(sacks) PP(into) (13.21) In the standard type of lexicalized grammar, we actually make a further exten- sion, which is to associate the head tag , the part-of-speech tags of the headwords, Head tag with the non-terminal symbols as well. Each rule is thus lexicalized by both the VPˆS VPˆVP PPˆVP NPˆPP NNS works NN advertising IN if VB see TO to VPˆS VPˆVP SBARˆVP SˆSBAR VPˆS VBZˆVP works NPˆS NNˆNP advertising INˆSBAR if VBˆVP see TOˆVP to Figure 13.9 An incorrect parse even with a parent-annotated parse (left). The correct parse (right), was produced by a grammar in which the pre-terminal nodes have been split, allowing the probabilistic grammar to capture the fact that if prefers sentential complements. Adapted from Klein and Manning (2003b) .
Image of page 225
226 C HAPTER 13 S TATISTICAL P ARSING headword and the head tag of each constituent resulting in a format for lexicalized rules like VP(dumped,VBD) ! VBD(dumped,VBD) NP(sacks,NNS) PP(into,P) (13.22) We show a lexicalized parse tree with head tags in Fig. 13.10 , extended from Fig.
Image of page 226

Info icon This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Image of page 227
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

What students are saying

  • Left Quote Icon

    As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

    Student Picture

    Kiran Temple University Fox School of Business ‘17, Course Hero Intern

  • Left Quote Icon

    I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

    Student Picture

    Dana University of Pennsylvania ‘17, Course Hero Intern

  • Left Quote Icon

    The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

    Student Picture

    Jill Tulane University ‘16, Course Hero Intern