tailieunhanh - Báo cáo khoa học: "Improving Chinese Semantic Role Labeling with Rich Syntactic Features"

Developing features has been shown crucial to advancing the state-of-the-art in Semantic Role Labeling (SRL). To improve Chinese SRL, we propose a set of additional features, some of which are designed to better capture structural information. Our system achieves Fmeasure, a significant improvement over the best reported performance . We are further concerned with the effect of parsing in Chinese SRL. We empirically analyze the two-fold effect, grouping words into constituents and providing syntactic information. . | Improving Chinese Semantic Role Labeling with Rich Syntactic Features Weiwei Sun Department of Computational Linguistics Saarland University German Research Center for Artificial Intelligence DFKI D-66123 Saarbriicken Germany wsun@ Abstract Developing features has been shown crucial to advancing the state-of-the-art in Semantic Role Labeling SRL . To improve Chinese SRL we propose a set of additional features some of which are designed to better capture structural information. Our system achieves F-measure a significant improvement over the best reported performance . We are further concerned with the effect of parsing in Chinese SRL. We empirically analyze the two-fold effect grouping words into constituents and providing syntactic information. We also give some preliminary linguistic explanations. 1 Introduction Previous work on Chinese Semantic Role Labeling SRL mainly focused on how to implement SRL methods which are successful on English. Similar to English parsing is a standard pre-processing for Chinese SRL. Many features are extracted to represent constituents in the input parses Sun and Jurafsky 2004 Xue 2008 Ding and Chang 2008 . By using these features semantic classifiers are trained to predict whether a constituent fills a semantic role. Developing features that capture the right kind of information encoded in the input parses has been shown crucial to advancing the state-of-the-art. Though there has been some work on feature design in Chinese SRL information encoded in the syntactic trees is not fully exploited and requires more research effort. In this paper we propose a set of additional The work was partially completed while this author was at Peking University. features some of which are designed to better capture structural information of sub-trees in a given parse. With help of these new features our system achieves F-measure with hand-crafted parses. Comparison with the best reported results Xue 2008 .