Implicit Role Linking on Chinese Discourse: Exploiting Explicit Roles and Frame-to-Frame Relations

Abstract

There is a growing interest in researching null instantiations, which are those implicit semantic arguments. Many of these implicit arguments can be linked to referents in context, and their discoveries are of great benefits to semantic processing. We address the issue of automatically identifying and resolving implicit arguments in Chinese discourse. For their resolutions, we present an approach that combines the information about overtly labeled arguments and frame-to-frame relations defined by FrameNet. Experimental results on our created corpus demonstrate the effectiveness of our approach.

Unsupervised Learning of Prototypical Fillers for Implicit Semantic Role Labeling

“…State-of-the-art approaches to implicit SRL (iSRL) are supervised and need a groundwork of hand-annotated training data -which is costly, extremely sparse, limited to only a handful of predicates, and requires careful feature engineering (Gerber and Chai, 2012;Silberer and Frank, 2012;Li et al, 2015). A first attempt has been made to combine the scarce resources available (Feizabadi and Padó, 2015), but given the great diversity of predicatespecific roles and enormous complexity of the task, the main issues remain (Chen et al, 2010).…”