Frame-Semantic Parsing
Citations Over TimeTop 1% of 2013 papers
Abstract
Frame semantics is a linguistic theory that has been instantiated for English in the FrameNet lexicon. We solve the problem of frame-semantic parsing using a two-stage statistical model that takes lexical targets (i.e., content words and phrases) in their sentential contexts and predicts frame-semantic structures. Given a target in context, the first stage disambiguates it to a semantic frame. This model uses latent variables and semi-supervised learning to improve frame disambiguation for targets unseen at training time. The second stage finds the target's locally expressed semantic arguments. At inference time, a fast exact dual decomposition algorithm collectively predicts all the arguments of a frame at once in order to respect declaratively stated linguistic constraints, resulting in qualitatively better structures than naïve local predictors. Both components are feature-based and discriminatively trained on a small set of annotated frame-semantic parses. On the SemEval 2007 benchmark data set, the approach, along with a heuristic identifier of frame-evoking targets, outperforms the prior state of the art by significant margins. Additionally, we present experiments on the much larger FrameNet 1.5 data set. We have released our frame-semantic parser as open-source software.
Related Papers
- → Semantic Role Labeling with Neural Network Factors(2015)131 cited
- → A Generative Model for Semantic Role Labeling(2003)78 cited
- → Beyond sentence-level semantic role labeling: linking argument structures in discourse(2012)10 cited
- → Semantic Role Labeling for Russian Language Based on Russian FrameBank(2015)2 cited
- → Semantic Frames and Visual Scenes: Learning Semantic Role Inventories from Image and Video Descriptions(2017)2 cited