jurafsky&martin_3rdEd_17 (1).pdf

The need for complex hand crafted features and have

Info icon This preview shows pages 258–260. Sign up to view the full content.

the need for complex, hand-crafted features and have been particularly effective at overcoming the data sparsity issues normally associated training transition-based parsers.
Image of page 258

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

14.4 T RANSITION -B ASED D EPENDENCY P ARSING 259 14.4.2 Advanced Methods in Transition-Based Parsing The basic transition-based approach can be elaborated in a number of ways of ways to improve performance by addressing some of the most obvious flaws in the ap- proach. Alternative Transition Systems The arc-standard transition system described above is only one of many possible sys- tems. A frequently used alternative is the arc eager transition system. The arc eager arc eager approach gets its name from its ability to assert rightward relations much sooner than in the arc standard approach. To see this, let’s revisit the arc standard trace of Example 14.7 , repeated here. Book the flight through Houston dobj det nmod case root Consider the dependency relation between book and flight in this analysis. As is shown in Fig. 14.8 , an arc-standard approach would assert this relation at Step 8, despite the fact that book and flight first come together on the stack much earlier at Step 4. The reason this relation can’t be captured at this point is due to the presence of the post-nominal modifier through Houston . In an arc-standard approach, depen- dents are removed from the stack as soon as they are assigned their heads. If flight had been assigned book as its head in Step 4, it would no longer be available to serve as the head of Houston . While this delay doesn’t cause any issues in this example, in general the longer a word has to wait to get assigned its head the more opportunities there are for something to go awry. The arc-eager system addresses this issue by allowing words to be attached to their heads as early as possible, before all the subsequent words dependent on them have been seen. This is accomplished through minor changes to the LEFT A RC and RIGHT A RC operators and the addition of a new REDUCE operator. LEFT A RC : Assert a head-dependent relation between the word at the front of the input buffer and the word at the top of the stack; pop the stack. RIGHT A RC : Assert a head-dependent relation between the word on the top of the stack and the word at front of the input buffer; shift the word at the front of the input buffer to the stack. SHIFT : Remove the word from the front of the input buffer and push it onto the stack. REDUCE : Pop the stack. The LEFT A RC and RIGHT A RC operators are applied to the top of the stack and the front of the input buffer, instead of the top two elements of the stack as in the arc-standard approach. The RIGHT A RC operator now moves the dependent to the stack from the buffer rather than removing it, thus making it available to serve as the head of following words. The new REDUCE operator removes the top element from the stack. Together these changes permit a word to be eagerly assigned its head and still allow it to serve as the head for later dependents. The trace shown in Fig.
Image of page 259
Image of page 260
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