A Joint Sequential and Relational Model for Frame-Semantic Parsing
By Bishan Yang, Tom Michael Mitchell. 2017
67 citations recorded by the source corpus.
We introduce a new method for frame-semantic parsing that significantly improves the prior state of the art. Our model leverages the advantages of a deep bidirectional LSTM network which predicts semantic role labels word by word and a relational network which predicts semantic roles for individual text expressions in relation to a predicate. The two networks are integrated into a single model via knowledge distillation, and a unified graphical model is employed to jointly decode frames and semantic roles during inference. Experiments on the standard FrameNet data show that our model significantly outperforms existing neural and non-neural approaches, achieving a 5.7 F1 gain over the current state of the art, for full frame structure extraction.
Subfields: Artificial Intelligence, Molecular Biology
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Luke S. Zettlemoyer
- Noah A. Smith
- Mohit Bansal
- Yejin Choi
- Hannaneh Hajishirzi
- Percy Liang
- Graham Neubig
- Yoav Goldberg
In Molecular Biology
- Luke S. Zettlemoyer
- Noah A. Smith
- Luheng He
- Sam Thomson
- Kenton C. T. Lee
- Chris Dyer
- Nicholas FitzGerald
- Swabha Swayamdipta
Citations in the corpus
- Large-Scale QA-SRL Parsing (2018, background): “Several recent works have explored neural models for SRL tasks (Collobert and Weston, 2007; FitzGerald et al., 2015; Swayamdipta et al., 2017; Yang and Mitchell, 2017), many of which employ a BIO encoding (Zhou and Xu, 2015; He et al., 2017).”
- Syntactic Scaffolds for Semantic Structures (2018, methodology): “Using syntax as T2 in a pipeline is perhaps the most common approach for semantic structure prediction (Toutanova et al., 2008; Yang and Mitchell, 2017; Wiseman et al., 2016).2 However, pipelines introduce the problem of cascading errors (T2’s mistakes affect the performance, and perhaps the…”
- Jointly Predicting Predicates and Arguments in Neural Semantic Role Labeling (2018, background): “Our span-graph formulation overcomes a key limitation of semi-markov and BIO-based models (Kong et al., 2016; Zhou and Xu, 2015; Yang and Mitchell, 2017; He et al., 2017; Tan et al., 2018): it can model overlapping spans across different predicates in the same output structure (see Figure 1).”