Loading...
Please wait, while we are loading the content...
Similar Documents
Joint Inference of Entities, Relations, and Coreference
| Content Provider | CiteSeerX |
|---|---|
| Author | Mccallum, Andrew Riedel, Sebastian Martin, Brian Zheng, Jiaping Singh, Sameer |
| Abstract | Although joint inference is an effective approach to avoid cascad-ing of errors when inferring multiple natural language tasks, its application to information extraction has been limited to modeling only two tasks at a time, leading to modest improvements. In this paper, we focus on the three crucial tasks of automated extraction pipelines: entity tagging, relation extraction, and coreference. We propose a single, joint graphical model that represents the various dependencies between the tasks, allowing flow of uncertainty across task boundaries. Since the resulting model has a high tree-width and contains a large number of variables, we present a novel extension to belief propagation that sparsifies the domains of variables during in-ference. Experimental results show that our joint model consistently improves results on all three tasks as we represent more dependen-cies. In particular, our joint model obtains 12 % error reduction on tagging over the isolated models. 1. |
| File Format | |
| Access Restriction | Open |
| Subject Keyword | Effective Approach Novel Extension Various Dependency Joint Graphical Model Crucial Task Isolated Model Relation Extraction Joint Inference Task Boundary Entity Tagging Automated Extraction Pipeline Large Number Error Reduction Joint Model Modest Improvement Information Extraction High Tree-width Experimental Result Multiple Natural Language Task |
| Content Type | Text |
