| Experimental Design | Structural Features Features in this category target primarily content selection and influence appropriate choice at the field level: |
| Problem Formulation | 2We also store field information to compute structural features , described in Section 4.2. |
| Results | Addition of the structural features further boosts performance. |
| Results | We tackle this issue with the inclusion of nonlocal structural features . |
| Corporate Acquisitions | While newswire documents are mostly unstructured, structural features are used to indicate whether any of the purchaser, acquired and seller text spans appears in |
| Corporate Acquisitions | Removing the inter type and structural features mildly hurt performance, on average. |
| Seminar Extraction Task | No structural features No semantic features No unification Individual fields |
| Seminar Extraction Task | As shown in the table, removing the structural features hurt performance consistently across fields. |
| Higher-order Constituent Parsing | Some back-off structural features are used for smoothing, which cannot be presented due to limited space. |
| Higher-order Constituent Parsing | Adding structural features , each involving a least a neighboring rule instance, makes it a higher-order parsing model. |
| Higher-order Constituent Parsing | Because all structures above the current rule instance is not determined yet, the computation of its nonlocal structural features , e. g., parent and sibling features, has to be delayed until it joins an upper level structure. |