The effect of alternative tree representations on tree bank grammars

Computer Science – Computation and Language

Scientific paper

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

Adds missing bibliography (sorry!), 11 pages, to appear in Proceedings of NeMLAP 3, uses epic.sty and eepic.sty

Scientific paper

The performance of PCFGs estimated from tree banks is sensitive to the particular way in which linguistic constructions are represented as trees in the tree bank. This paper presents a theoretical analysis of the effect of different tree representations for PP attachment on PCFG models, and introduces a new methodology for empirically examining such effects using tree transformations. It shows that one transformation, which copies the label of a parent node onto the labels of its children, can improve the performance of a PCFG model in terms of labelled precision and recall on held out data from 73% (precision) and 69% (recall) to 80% and 79% respectively. It also points out that if only maximum likelihood parses are of interest then many productions can be ignored, since they are subsumed by combinations of other productions in the grammar. In the Penn II tree bank grammar, almost 9% of productions are subsumed in this way.

No associations

LandOfFree

Say what you really think

Search LandOfFree.com for scientists and scientific papers. Rate them and share your experience with other people.

Rating

The effect of alternative tree representations on tree bank grammars does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with The effect of alternative tree representations on tree bank grammars, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and The effect of alternative tree representations on tree bank grammars will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFWR-SCP-O-66404

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.