Home Linguistics & Semiotics Chapter 4. How to compare speed and accuracy of syntactic parsers
Chapter
Licensed
Unlicensed Requires Authentication

Chapter 4. How to compare speed and accuracy of syntactic parsers

  • Gertjan van Noord
View more publications by John Benjamins Publishing Company
Search
Crossroads Semantics
This chapter is in the book Crossroads Semantics

Abstract

The paper introduces a methodological innovation as well as a practical innovation. Firstly, two scenarios are introduced to compare accurate, but slow parsers on the one hand, with faster, but less accurate parsers on the other hand. Secondly, a corpus-based technique is described to improve the efficiency of wide-coverage high-accuracy parsers. By keeping track of the derivation steps which lead to the best parse for a very large collection of sentences, the parser learns which parse steps can be filtered without significant loss in parsing accuracy, but with an important increase in parsing efficiency. Experimental results with the Alpino parser for Dutch indicate that the technique yields much faster parsers that perform with almost the same level of accuracy. An interesting characteristic of our approach is that it is self-learning, in the sense that it uses unannotated corpora.

Abstract

The paper introduces a methodological innovation as well as a practical innovation. Firstly, two scenarios are introduced to compare accurate, but slow parsers on the one hand, with faster, but less accurate parsers on the other hand. Secondly, a corpus-based technique is described to improve the efficiency of wide-coverage high-accuracy parsers. By keeping track of the derivation steps which lead to the best parse for a very large collection of sentences, the parser learns which parse steps can be filtered without significant loss in parsing accuracy, but with an important increase in parsing efficiency. Experimental results with the Alpino parser for Dutch indicate that the technique yields much faster parsers that perform with almost the same level of accuracy. An interesting characteristic of our approach is that it is self-learning, in the sense that it uses unannotated corpora.

Chapters in this book

  1. Prelim pages i
  2. Dedication v
  3. Table of contents vii
  4. Introduction 1
  5. Chapter 1. Bridging theoretical and experimental linguistic research 9
  6. Data and its use
  7. Chapter 2. Experimental research 23
  8. Chapter 3. Finding long-distance dependencies in the Lassy Corpus 39
  9. Chapter 4. How to compare speed and accuracy of syntactic parsers 57
  10. Chapter 5. Adposition clusters in Dutch 77
  11. Chapter 6. Polarity licensing and intervention by conjunction 93
  12. Chapter 7. Frequential test of (S)OV as unmarked word order in Dutch and German clauses 107
  13. Chapter 8. Kratzer’s effect in the nominal domain 125
  14. Chapter 9. Is bilingual speech production language-specific or non-specific? 139
  15. Chapter 10. Prosody of restrictive and appositive relative clauses in Dutch and German 155
  16. Chapter 11. Licensing distributivity 177
  17. Implementation and theory building
  18. Chapter 12. Extending categorial grammar to phonology 193
  19. Chapter 13. Stacking up for the long way down 207
  20. Chapter 14. Meaning between algebra and culture 227
  21. Chapter 15. Whether you like it or not, this is a paper about or not 249
  22. Chapter 16. Between desire and necessity 263
  23. Chapter 17. Inner aspect and the comparative quantifiers 281
  24. Chapter 18. The expressive en maar -construction 305
  25. Index 327
https://doi.org/10.1075/z.210.04van

Chapters in this book

  1. Prelim pages i
  2. Dedication v
  3. Table of contents vii
  4. Introduction 1
  5. Chapter 1. Bridging theoretical and experimental linguistic research 9
  6. Data and its use
  7. Chapter 2. Experimental research 23
  8. Chapter 3. Finding long-distance dependencies in the Lassy Corpus 39
  9. Chapter 4. How to compare speed and accuracy of syntactic parsers 57
  10. Chapter 5. Adposition clusters in Dutch 77
  11. Chapter 6. Polarity licensing and intervention by conjunction 93
  12. Chapter 7. Frequential test of (S)OV as unmarked word order in Dutch and German clauses 107
  13. Chapter 8. Kratzer’s effect in the nominal domain 125
  14. Chapter 9. Is bilingual speech production language-specific or non-specific? 139
  15. Chapter 10. Prosody of restrictive and appositive relative clauses in Dutch and German 155
  16. Chapter 11. Licensing distributivity 177
  17. Implementation and theory building
  18. Chapter 12. Extending categorial grammar to phonology 193
  19. Chapter 13. Stacking up for the long way down 207
  20. Chapter 14. Meaning between algebra and culture 227
  21. Chapter 15. Whether you like it or not, this is a paper about or not 249
  22. Chapter 16. Between desire and necessity 263
  23. Chapter 17. Inner aspect and the comparative quantifiers 281
  24. Chapter 18. The expressive en maar -construction 305
  25. Index 327
Sign up now to receive a 20% welcome discount
Institutional Access
How does access work?
Have an idea on how to improve our website?
Please write us.
© 2025 De Gruyter Brill
Downloaded on 29.9.2025 from https://www.degruyterbrill.com/document/doi/10.1075/z.210.04van/html
Scroll to top button