tailieunhanh - Báo cáo khoa học: "A Comparative Study on Generalization of Semantic Roles in FrameNet"
A number of studies have presented machine-learning approaches to semantic role labeling with availability of corpora such as FrameNet and PropBank. These corpora define the semantic roles of predicates for each frame independently. Thus, it is crucial for the machine-learning approach to generalize semantic roles across different frames, and to increase the size of training instances. This paper explores several criteria for generalizing semantic roles in FrameNet: role hierarchy, human-understandable descriptors of roles, semantic types of filler phrases, and mappings from FrameNet roles to thematic roles of VerbNet. . | A Comparative Study on Generalization of Semantic Roles in FrameNet Yuichiroh Matsubayashil Naoaki Okazaki Jun ichi Tsujiitt Department of Computer Science University of Tokyo Japan School of Computer Science University of Manchester UK National Centre for Text Mining UK y-matsu okazaki tsujii @ Abstract A number of studies have presented machine-learning approaches to semantic role labeling with availability of corpora such as FrameNet and PropBank. These corpora define the semantic roles of predicates for each frame independently. Thus it is crucial for the machine-learning approach to generalize semantic roles across different frames and to increase the size of training instances. This paper explores several criteria for generalizing semantic roles in FrameNet role hierarchy human-understandable descriptors of roles semantic types of filler phrases and mappings from FrameNet roles to thematic roles of VerbNet. We also propose feature functions that naturally combine and weight these criteria based on the training data. The experimental result of the role classification shows and improvements in error reduction rate and macro-averaged F1 score respectively. We also provide in-depth analyses of the proposed criteria. 1 Introduction Semantic Role Labeling SRL is a task of analyzing predicate-argument structures in texts. More specifically SRL identifies predicates and their arguments with appropriate semantic roles. Resolving surface divergence of texts . voice of verbs and nominalizations into unified semantic representations SRL has attracted much attention from researchers into various NLP applications including question answering Narayanan and Harabagiu 2004 Shen and Lapata 2007 PropBank FrameNet Frame Commerce_buy Roles ARG0 ARG1 ARG2 ARG3 ARG4 . buyer thing bought seller paid benefactive Buyer Goods Seller Money Recipient . Figure 1 A comparison of frames for defined in PropBank and FrameNet Moschitti et al.
đang nạp các trang xem trước