Combining PCFG-LA models with dual decomposition: a case study with function labels and binarization
Le Roux, Joseph, Rozenknop, Antoine and Foster, JenniferORCID: 0000-0002-7789-4853
(2013)
Combining PCFG-LA models with dual decomposition: a case study with function labels and binarization.
In: International Conference on Empirical Methods in Natural Language Processing, 18-21 Oct 2013, Seattle, WA..
It has recently been shown that different NLP models can be effectively combined using dual decomposition. In this paper we demonstrate that PCFG-LA parsing models are suit- able for combination in this way. We experiment 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 Section 23 – this represents an absolute improvement of 0.7 and an error reduction rate of 7% over a strong PCFG-LA product-model base- line. Although we experiment only with binarization and function labels in this study, there is much scope for applying this approach to other grammar extraction strategies.