Sciweavers

Share
ACL
2010

Hierarchical Joint Learning: Improving Joint Parsing and Named Entity Recognition with Non-Jointly Labeled Data

8 years 21 days ago
Hierarchical Joint Learning: Improving Joint Parsing and Named Entity Recognition with Non-Jointly Labeled Data
One of the main obstacles to producing high quality joint models is the lack of jointly annotated data. Joint modeling of multiple natural language processing tasks outperforms single-task models learned from the same data, but still underperforms compared to single-task models learned on the more abundant quantities of available single-task annotated data. In this paper we present a novel model which makes use of additional single-task annotated data to improve the performance of a joint model. Our model utilizes a hierarchical prior to link the feature weights for shared features in several single-task models and the joint model. Experiments on joint parsing and named entity recognition, using the OntoNotes corpus, show that our hierarchical joint model can produce substantial gains over a joint model trained on only the jointly annotated data.
Jenny Rose Finkel, Christopher D. Manning
Added 28 Feb 2011
Updated 28 Feb 2011
Type Journal
Year 2010
Where ACL
Authors Jenny Rose Finkel, Christopher D. Manning
Comments (0)
books