Greedy, Joint Syntactic-Semantic Parsing with Stack LSTMs

By Swabha Swayamdipta, Miguel Ballesteros, Chris Dyer, Noah A. Smith. 2016

63 citations recorded by the source corpus.

We present a transition-based parser that jointly produces syntactic and semantic dependencies. It learns a representation of the entire algorithm state, using stack long short-term memories. Our greedy inference algorithm has linear time, including feature extraction. On the CoNLL 2008--9 English shared tasks, we obtain the best published parsing performance among models that jointly learn syntax and semantics.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

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

In Computer Vision and Pattern Recognition

Citations in the corpus

Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling (2017, background): “A more modern (e.g., based on LSTMs) and effective rein-carnation of this line of research has been proposed in Swayamdipta et al. (2016).”
Deep Semantic Role Labeling: What Works and What’s Next (2017, methodology): “Neural methods have also been used as classifiers in transition-based SRL systems (Henderson et al., 2013; Swayamdipta et al., 2016).”
Deep Multitask Learning for Semantic Dependency Parsing (2017, methodology): “Syntactic parsing could be treated as yet another output task, as explored in Lluı́s et al. (2013) and in the transition-based frameworks of Henderson et al. (2013) and Swayamdipta et al. (2016).”
A Joint Sequential and Relational Model for Frame-Semantic Parsing (2017, background): “Zhou and Xu (2015) employs a deep bi-directional LSTM (DB-LSTM) network and achieves stateof-the-art results on PropBank-style SRL. Recently, Swayamdipta et al. (2016) employs stack LSTMs (Dyer et al., 2015) for joint syntacticsemantic dependency parsing.”
A Simple and Accurate Syntax-Agnostic Neural Model for Dependency-based Semantic Role Labeling (2017, background): “…is not practical (Titov et al., 2009; Gesmundo et al., 2009; Henderson et al., 2013), neural SRL models now also out-perform their traditional counterparts on standard benchmarks for English (FitzGerald et al., 2015; Roth and Lapata, 2016; Swayamdipta et al., 2016; Foland and Martin, 2015).”
DyNet: The Dynamic Neural Network Toolkit (2017, methodology): “…in development of methods for named entity recognition [40] ( https://github.com/clab/stack-lstm-ner ), POS-tagging [49], semantic role labeling [60] ( https://github.com/clab/joint-lstm-parser ), punctuation prediction [5] ( https://github.com/miguelballesteros/LSTM-punctuation ), and…”
Syntactic Scaffolds for Semantic Structures (2018, background): “The motivation behind joint learning of syntactic and semantic representations is that any one task is helpful in predicting the other (Lluı́s and Màrquez, 2008; Lluı́s et al., 2013; Henderson et al., 2013; Swayamdipta et al., 2016).”