Semantic Argument Classification Exploiting Argument Interdependence
نویسندگان
چکیده
This paper describes our research on automatic semantic argument classification, using the PropBank data [Kingsbury et al., 2002]. Previous research employed features that were based either on a full parse or shallow parse of a sentence. These features were mostly based on an individual semantic argument and the relation between the predicate and a semantic argument, but they did not capture the interdependence among all arguments of a predicate. In this paper, we propose the use of the neighboring semantic arguments of a predicate as additional features in determining the class of the current semantic argument. Our experimental results show significant improvement in the accuracy of semantic argument classification after exploiting argument interdependence. Argument classification accuracy on the standard Section 23 test set improves to 90.50%, representing a relative error reduction of 18%.
منابع مشابه
Improving Chinese Semantic Role Classification with Hierarchical Feature Selection Strategy
In recent years, with the development of Chinese semantically annotated corpus, such as Chinese Proposition Bank and Normalization Bank, the Chinese semantic role labeling (SRL) task has been boosted. Similar to English, the Chinese SRL can be divided into two tasks: semantic role identification (SRI) and classification (SRC). Many features were introduced into these tasks and promising results...
متن کاملDistributed Representations for Unsupervised Semantic Role Labeling
We present a new approach for unsupervised semantic role labeling that leverages distributed representations. We induce embeddings to represent a predicate, its arguments and their complex interdependence. Argument embeddings are learned from surrounding contexts involving the predicate and neighboring arguments, while predicate embeddings are learned from argument contexts. The induced represe...
متن کاملA Semantic Kernel for Predicate Argument Classification
Automatically deriving semantic structures from text is a challenging task for machine learning. The flat feature representations, usually used in learning models, can only partially describe structured data. This makes difficult the processing of the semantic information that is embedded into parse-trees. In this paper a new kernel for automatic classification of predicate arguments has been d...
متن کاملMulti-Argument Classification for Semantic Role Labeling
This paper describes a Multi-Argument Classification (MAC) approach to Semantic Role Labeling. The goal is to exploit dependencies between semantic roles by simultaneously classifying all arguments as a pattern. Argument identification, as a pre-processing stage, is carried at using the improved Predicate-Argument Recognition Algorithm (PARA) developed by Lin and Smith (2006). Results using sta...
متن کاملCommodified Discourses, Commodifying Discourses: In Pursuit of a Theoretical Model on the Constitutive Functioning of Academic Discourse in Marketization of Higher Education
Inspired by Fairclough's suggestion of the idea of commodification in higher education, particularly in terms of "the marketization of the discursive practices of universities" (1993, p. 143), the author of the present paper proposes a theoretical basis within which the constitutive functioning of academic discourse in the mentioned process can be understood. In this attempt, Althusser's chain...
متن کامل