.png){kind=icon}
Return
Tree kernel-based semantic role labeling with enriched parse tree structure
.png){kind=icon}
PRE
AI
DOI：10.1016/j.ipm.2010.08.005.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Shallow semantic parsing assigns a simple structure (such as WHO did WHAT to WHOM, WHEN, WHERE, WHY, and HOW) to each predicate in a sentence. It plays a critical role in event-based information extraction and thus is important for deep information processing and management. This paper proposes a tree kernel method for a particular shallow semantic parsing task, called semantic role labeling (SRL), with an enriched parse tree structure. First, a new tree kernel is presented to effectively capture the inherent structured knowledge in a parse tree by enabling the standard convolution tree kernel with context-sensitiveness via considering ancestral information of substructures and approximate matching via allowing insertion/deletion/substitution of tree nodes in the substructures. Second, an enriched parse tree structure is proposed to both well preserve the necessary structured information and effectively avoid noise by differentiating various portions of the parse tree structure. Evaluation on the CoNLL'2005 shared task shows that both the new tree kernel and the enriched parse tree structure contribute much in SRL and our tree kernel method significantly outperforms the state-of-the-art tree kernel methods. Moreover, our tree kernel method is proven rather complementary to the state-of-the-art feature-based methods in that it can better capture structural parse tree information. (C) 2010 Elsevier Ltd. All rights reserved.
Keywords:
Semantic role labeling
Enriched parse tree structure
Convolution tree kernel
Context-sensitiveness
Approximate matching
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
I
IF:
6.9
Papers:
5.2K
Citations:
1.4W
Organization
Cited Papers
.png){kind=icon}
ShareSave
ShareSaveShareSaveShareSaveShareSaveShareSave
View more