Emulation of Human Sentence Processing using an Automatic Dependency Shift-Reduce Parser

Atanas Chanev

Abstract

The methods of NLP and Cognitive Science can complement each other for the design of better models of the human sentence processing mechanism, on the one hand, and the development of better natural language parsers, on the other. In this paper, we show the performance of an automatic parser consistent with the architecture of the human parser of [2] on various human sentence processing experimental materials. Moreover, we use a linking hypothesis based on the concept of surprisal [9] to explain human reaction time patterns. Although our results are generally not consistent with the human performance, our emu- lations contribute to understanding the architecture of the human parser and its disambiguation strategies better. We also suggest that these strategies may possibly be used for improving the performance of automatic parsers.

References

  1. Attardi, G., Dell'Orletta, F., Simi, M., Chanev, A. & Ciaramita, M. (2007). Multilingual Dependency Parsing and Domain Adaptation using DeSR. In Proc. of the shared task session of EMNLP-CoNLL 2007, Prague
  2. Chanev, A. (2007). Investigating the relationship between automatic parsing and human sentence processing. PhD thesis, University of Trento
  3. Ciaramita, M., & Altun, Y. (2006). Broad-coverage sense disambiguation and information extraction with a supersense sequence tagger. In Proc. of EMNLP 2006.
  4. Crammer, K. & Singer, Y. (2003). Ultraconservative online algorithms for multiclass problems. Journal of Machine Learning Research, 3, 951-991.
  5. Giménez, J., & Márquez , L. (2004). SVMTool: A general POS tagger generator based on Support Vector Machines. Proc. of LREC'04, Lisbon, Portugal.
  6. Grodner, D. & Gibson, E. (2005). Some consequences of the serial nature of linguistic input. Cognitive Science, 29(2), 261-290.
  7. Hale, J. (2001). A probabilistic Earley parser as a psycholinguistic model. In Proc. of the 2nd Meeting of NAACL.
  8. Jaeger, F., Fedorenko, E., & Gibson, E. (2005). Dissociation between production and comprehension complexity. Poster Presentation at the 18th CUNY Sentence Processing Conference, University of Arizona.
  9. Levy, R. (2008). Expectation-based syntactic comprehension. Cognition, 106 (3), 1126- 1177.
  10. Marcus, M. P., Santorini, B., & Marcinkiewicz, M. A. (1993). Building a large annotated corpus of English: The Penn Treebank. Computational Linguistics, 19 (2).
  11. Melc?uk, I. (1988). Dependency syntax: Theory and practice. State University of New York Press.
  12. Nivre, J. (2006). Inductive Dependency Parsing. Springer.
  13. Nivre, J., Hall, J., Kübler, S., McDonald, R., Nilsson, J., Riedel, S. & Yuret, D. (2007). The CoNLL 2007 Shared Task on Dependency Parsing. In Proc. of the shared task session of EMNLP-CoNLL 2007, Prague
  14. Stolcke, A. (1995). An efficient probabilistic context-free parsing algorithm that computes prefix probabilities. Computational Linguistics, 21(2), 165-201.
  15. Tabor, W., Galantucci, B., and Richardson, D. (2004). Effects of merely local syntactic coherence on sentence processing. Journal of Memory and Language, 50(4), 355-370.
  16. Traxler, M. J., Pickering, M. J., & Clifton, C. (1998). Adjunct attachment is not a form of lexical ambiguity resolution. Journal of Memory and Language, 39, 558-592.
Download


Paper Citation


in Harvard Style

Chanev A. (2008). Emulation of Human Sentence Processing using an Automatic Dependency Shift-Reduce Parser . In Proceedings of the 5th International Workshop on Natural Language Processing and Cognitive Science - Volume 1: NLPCS, (ICEIS 2008) ISBN 978-989-8111-45-6, pages 137-146. DOI: 10.5220/0001732001370146


in Bibtex Style

@conference{nlpcs08,
author={Atanas Chanev},
title={Emulation of Human Sentence Processing using an Automatic Dependency Shift-Reduce Parser},
booktitle={Proceedings of the 5th International Workshop on Natural Language Processing and Cognitive Science - Volume 1: NLPCS, (ICEIS 2008)},
year={2008},
pages={137-146},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001732001370146},
isbn={978-989-8111-45-6},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 5th International Workshop on Natural Language Processing and Cognitive Science - Volume 1: NLPCS, (ICEIS 2008)
TI - Emulation of Human Sentence Processing using an Automatic Dependency Shift-Reduce Parser
SN - 978-989-8111-45-6
AU - Chanev A.
PY - 2008
SP - 137
EP - 146
DO - 10.5220/0001732001370146