Reproducing Chen & Manning (2014)

This page documents necessary steps to reproduce results of Chen & Manning (2014)^[1] for English (including re-implementation) and makes explicit decisions that aren't covered in the paper.

Obtain data: WSJ part of PENN Treebank. Section 02-21 for training, 22 for development, 23 for testing.
- I used this revised version: LDC2015T13
Constituent-to-dependency conversion:
1. LTH Constituent-to-Dependency Conversion Tool
  - Downloaded pennconverter
  - Command: java -jar pennconverter.jar -format=conllx -rightBranching=false -verbosity 2 -stopOnError
2. Stanford Basic Dependencies
  - TODO
Assign POS tags using Stanford POS tagger with ten-way jackknifing of the training data
- Reported accuracy: ≈ 97.3%
- I used version 3.6.0 downloaded here and followed instructions in the JavaDoc.
- Reused english-bidirectional-distsim.tagger.props (without distributional similarity since I don't have that resource). Fixed some problem: [1]

References

↑ Chen, D., & Manning, C. (2014). A Fast and Accurate Dependency Parser using Neural Networks. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) (pp. 740–750). Doha, Qatar: Association for Computational Linguistics.

[1] Chen, D., & Manning, C. (2014). A Fast and Accurate Dependency Parser using Neural Networks. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) (pp. 740–750). Doha, Qatar: Association for Computational Linguistics.

[1]