Combining PCFG-LA Models with Dual Decomposition: A Case Study with Function Labels and Binarization

Joseph Le Roux (1) , Antoine Rozenknop (1, 1) , Jennifer Foster (2)

1 LIPN - Laboratoire d'Informatique de Paris-Nord
2 DCU - School of Computing

It has recently been shown that different NLP models can be effectively combined using dual decomposition. In this paper we demon-strate that PCFG-LA parsing models are suit-able for combination in this way. We exper-iment with the different models which result from alternative methods of extracting a gram-mar from a treebank (retaining or discarding function labels, left binarization versus right binarization) and achieve a labeled Parseval F-score of 92.4 on Wall Street Journal Sec-tion 23 – this represents an absolute improve-ment of 0.7 and an error reduction rate of 7% over a strong PCFG-LA product-model base-line. Although we experiment only with bina-rization and function labels in this study, there is much scope for applying this approach to other grammar extraction strategies.

Mots clés: Parsing models; Dual decomposition

Domaines: Informatique et langage [cs.CL]

Joseph Le Roux, Antoine Rozenknop, Jennifer Foster. Combining PCFG-LA Models with Dual Decomposition: A Case Study with Function Labels and Binarization. the 2013 Conference on Empirical Methods in Natural Language Processing, Association of Computational Linguistics, Oct 2013, Seattle, United States. pp.1158-1169. ⟨hal-01075344⟩