1 / 12

The Exploration of Deterministic and Efficient Dependency Parsing

The Exploration of Deterministic and Efficient Dependency Parsing. National Central University , Taiwan Ming Chuan University , Taiwan. Yu-Chieh Wu Yue-Shi Lee Jie-Chi Yang. Date: 2006/6/8 Reporter: Yu-Chieh Wu. Context. Nivre ’ s method is a LINEAR-TIME parsing algorithm

Télécharger la présentation

The Exploration of Deterministic and Efficient Dependency Parsing

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. The Exploration of Deterministic and Efficient Dependency Parsing National Central University, Taiwan Ming Chuan University, Taiwan Yu-Chieh Wu Yue-Shi Lee Jie-Chi Yang Date: 2006/6/8 Reporter: Yu-Chieh Wu

  2. Context • Nivre’s method is a LINEAR-TIME parsing algorithm • But it presumed the projective grammar relation for text • One solution is to applying the psuedo projectivization (Nivre and Nilson, 2005) • In addition, non-projective words or roots were still kept in stack • Un-parsed words • In multilingual scenario, some languages annotated labels for roots

  3. In this paper • Extend the time efficiency of the Nivre’s method • DO NOT scan the word sequence multiple times • Perform the Niver’s algorithm • Only focused on the “UN-PARSED” words • Efficiently label the roots

  4. Parsed Text Nivre’s Parser Root Parser Post- Processor Un-Parsed Text Learner 1 Learner 2 Learner 3 Un-Parsed Words Un-Parsed Words System Overview

  5. Our solution is… • To reduce the un-parsed rate • We performed both • Forward parsing • Backward parsing directions (usually better) • To classify the remaining words in stacks • A root parser to identify the word is… • Root (including root label) or not root • To re-connect the non-projective words • A post-processor is used to re-construct the arcs • Exhaustive from the sentence start • Regardless its children

  6. Statistics of un-parsed rate (percentage)

  7. Wordi+1 Child0 Wordi-2 Wordi-1 Wordi ChildR Wordi+2 Bigrami+2 Bigrami+1 Bigrami Bigram Bigrami-1 Bigrami-2 Bigram BiPOS BiPOSi+2 BiPOS BiPOSi BiPOSi-1 BiPOSi-2 BiPOSi+1 Root Parser For each un-parsed words

  8. Experimental Results

  9. Parsing performance of different grained POS tags and forward/backward parsing directions

  10. Conclusion • In this paper, we investigate the how effect does the “fast parser” achieve • The employed features were quite simple • Only C/F-POS tag and word form • We extend the Nivre’s method • Root parser • Exhaustive post-processing

  11. Questions ?

  12. System Spec

More Related