Projects per year
We describe an approach to create a diverse set of predictions with spectral learning of latent-variable PCFGs (L-PCFGs). Our approach works by creating multiple spectral models where noise is added to the underlying features in the training set before the estimation of each model. We describe three ways to decode with multiple models. In addition, we describe a simple variant of the spectral algorithm for L-PCFGs that is fast and leads to compact models. Our experiments for natural language parsing, for English and German, show that we get a significant improvement over baselines comparable to state of the art. For English, we achieve the F1 score of 90.18, and for German we achieve the F1 score of 83.38.
|Title of host publication||The 2015 Conference on Empirical Methods on Natural Language Processing|
|Number of pages||10|
|Publication status||Published - 20 Sep 2015|
FingerprintDive into the research topics of 'Diversity in Spectral Learning for Natural Language Parsing'. Together they form a unique fingerprint.
- 1 Finished