Semantic Role Labeling with Neural Network Factors

By Nicholas FitzGerald, Oscar Täckström, Kuzman Ganchev, Dipanjan Das. 2015

152 citations recorded by the source corpus.

We present a new method for semantic role labeling in which arguments and semantic roles are jointly embedded in a shared vector space for a given predicate. These embeddings belong to a neural network, whose output represents the potential functions of a graphical model designed for the SRL task. We consider both local and structured learning methods and obtain strong results on standard PropBank and FrameNet corpora with a straightforward product-of-experts model. We further show how the model can learn jointly from PropBank and FrameNet annotations to obtain additional improvements on the smaller FrameNet dataset.

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

In Molecular Biology

Citations in the corpus

Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling (2017, methodology): “5 As FitzGerald et al. (2015) and Marcheggiani et al. (2017), instead of using a ﬁxed matrix W l,r or simply assuming that W l,r = W r , we jointly embed the role r and predicate lemma l using a non-linear transformation: where U is a parameter matrix, whereas q l ∈ d l and q r ∈ d r are randomly…”
Deep Semantic Role Labeling: What Works and What’s Next (2017, methodology): “More recently, neural methods have been employed on top of syntactic features (FitzGerald et al., 2015; Roth and Lapata, 2016).”
Linguistically-Informed Self-Attention for Semantic Role Labeling (2018, methodology): “FitzGerald et al. (2015) successfully employed neural networks by embedding lexicalized features and providing them as factors in the model of T¨ackstr¨om et al. (2015).”
Greedy, Joint Syntactic-Semantic Parsing with Stack LSTMs (2016, methodology): “Täckström et al. (2015) present an exact inference algorithm for SRL based on dynamic programming and their local and structured models make use of many syntactic features from a pipeline; our search procedure is greedy.”
Syntactic Scaffolds for Semantic Structures (2018, methodology): “Prior work for frame SRL has relied on predicted syntactic trees, in two different ways: by using syntax-based rules to prune out spans of text that are unlikely to contain any frame’s argument; and by using syntactic features in their statistical model (Das et al., 2014; Täckström et al., 2015; Fit”
A Joint Sequential and Relational Model for Frame-Semantic Parsing (2017, methodology): “…employs an ensemble with the product-of-experts (PoE) (Hinton, 2002); and FitzGerald (Local, PoE, Joint) indicates the best reported results in FitzGerald et al. (2015) joint inference of both frames and semantic roles, our model performs even better, achieving a 5.7 absolute F1 gain over the…”
End-to-End Learning for Structured Prediction Energy Networks (2017, methodology): “FitzGerald et al. (2015) extend this using neural network features and show improved results.”
Deep Multitask Learning for Semantic Dependency Parsing (2017, background): “(cid:1) NLP researchers have found that embedding discrete output labels into a low dimensional real space is an effective way to capture commonalities among them (Srikumar and Manning, 2014; Hermann et al., 2014; FitzGerald et al., 2015, inter alia ).”
Situation Recognition: Visual Semantic Role Labeling for Image Understanding (2016, methodology): “is used as the input to a fully connected layer which predicts potential values in our CRF, similar to neural networks used for semantic role labeling in sentences [15].”
A Sequence-to-Sequence Model for Semantic Role Labeling (2018, methodology): “that in contrast to the stronger models of FitzGerald et al. (2015); Zhou and Xu (2015) and He et al.”
Commonly Uncommon: Semantic Sparsity in Situation Recognition (2016, methodology): “The model is motivated by compositional models used for semantic role labeling [14] and allows us to trade-off the need to reduce parameters associated with nouns and expressivity.”
A Comprehensive Survey on Automatic Knowledge Graph Construction (2023, background): “Examples include NNF [174] and dependency path embedding [175].”
Neural Semantic Role Labeling with Dependency Path Embeddings (2016, methodology): “Foland and Martin (2015) extended their model and showcased significant improvements when including binary indicator features for dependency paths.”
Jointly Predicting Predicates and Arguments in Neural Semantic Role Labeling (2018, background): “The span representations also generalize the token-level representations in BIO-based models, letting the model dynamically decide which spans and roles to include, without using previously standard syntactic features (Pun-yakanok et al., 2008; FitzGerald et al., 2015).”
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).”
Cross-Sentence N-ary Relation Extraction with Graph LSTMs (2017, methodology): “Recently, neural models have been applied to semantic role labeling (FitzGerald et al., 2015; Roth and Lapata, 2016).”
A Simple and Accurate Syntax-Agnostic Neural Model for Dependency-based Semantic Role Labeling (2017, background): “Our syntax-agnostic method is simple and fast, and surpasses comparable approaches (no system combination, local inference) on the standard in-domain benchmark for English.”