jurafsky&martin_3rdEd_17 (1).pdf

In adapting this approach for dependency parsing we

Info icon This preview shows pages 250–253. Sign up to view the full content.

View Full Document Right Arrow Icon
from the left-hand side of the rule being matched. In adapting this approach for dependency parsing, we forgo the explicit use of a grammar and alter the reduce operation so that instead of adding a non-terminal to a parse tree, it introduces a dependency relation between a word and its head. More specifically, the reduce ac- tion is replaced with two possible actions: assert a head-dependent relation between the word at the top of the stack and the word below it, or vice versa. Figure 14.5 illustrates the basic operation of such a parser. A key element in transition-based parsing is the notion of a configuration which Configuration consists of a stack, an input buffer of words, or tokens, and a set of relations rep- resenting a dependency tree. Given this framework, the parsing process consists of a sequence of transitions through the space of possible configurations. The goal of
Image of page 250

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

View Full Document Right Arrow Icon
14.4 T RANSITION -B ASED D EPENDENCY P ARSING 251 S VP VP NP-TMP CD 29 NNP Nov PP-CLR NP NN director JJ nonexecutive DT a IN as NP NN board DT the VB join MD will NP-SBJ NNP Vinken S(join) VP(join) VP(join) NP-TMP(29) CD 29 NNP Nov PP-CLR(director) NP(director) NN director JJ nonexecutive DT a IN as NP(board) NN board DT the VB join MD will NP-SBJ(Vinken) NNP Vinken join 29 Nov director nonexecutive a as board the will Vinken Figure 14.4 A phrase-structure tree from the Wall Street Journal component of the Penn Treebank 3. this process is to find a final configuration where all the words have been accounted for and an appropriate dependency tree has been synthesized. To implement such a search, we’ll define a set of transition operators, which when applied to a configuration produce new configurations. Given this setup, we can view the operation of a parser as a search through a space of configurations for a sequence of transitions that leads from a start state to a desired goal state. At the start of this process we create an initial configuration in which the stack contains the
Image of page 251
252 C HAPTER 14 D EPENDENCY P ARSING Dependency Relations wn w1 w2 s2 ... s1 sn Parser Input buffer Stack Oracle Figure 14.5 Basic transition-based parser. The parser examines the top two elements of the stack and selects an action based on consulting an oracle that examines the current configura- tion. ROOT node, the word list is initialized with the set of the words or lemmatized tokens in the sentence, and an empty set of relations is created to represent the parse. In the final goal state, the stack and the word list should be empty, and the set of relations will represent the final parse. In the standard approach to transition-based parsing, the operators used to pro- duce new configurations are surprisingly simple and correspond to the intuitive ac- tions one might take in creating a dependency tree by examining the words in a single pass over the input from left to right (Covington, 2001) : Assign the current word as the head of some previously seen word, Assign some previously seen word as the head of the current word,
Image of page 252

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

View Full Document Right Arrow Icon
Image of page 253
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