Hierarchical Low-Rank Tensors for Multilingual Transfer Parsing
Author(s)Barzilay, Regina; Zhang, Yuan
MetadataShow full item record
Accurate multilingual transfer parsing typically relies on careful feature engineering. In this paper, we propose a hierarchical tensor-based approach for this task. This approach induces a compact feature representation by combining atomic features. However, unlike traditional tensor models, it enables us to incorporate prior knowledge about desired feature interactions, eliminating invalid feature combinations. To this end, we use a hierarchical structure that uses intermediate embeddings to capture desired feature combinations. Algebraically, this hierarchical tensor is equivalent to the sum of traditional tensors with shared components, and thus can be effectively trained with standard online algorithms. In both unsupervised and semi-supervised transfer scenarios, our hierarchical tensor consistently improves UAS and LAS over state-of-the-art multilingual transfer parsers and the traditional tensor model across 10 different languages.
DepartmentMassachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory; Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing
Association for Computational Linguistics
Zhang, Yuan and Regina Barzilay. "Hierarchical Low-Rank Tensors for Multilingual Transfer Parsing." 2015 Conference on Empirical Methods in Natural Language Processing, Lisbon, Portugal, 17-21 September, 2015. Association for Computational Linguistics, 2015, pp. 1857–1867.
Author's final manuscript