A Simple and Accurate Syntax-Agnostic Neural Model for Dependency-based Semantic Role Labeling

By Diego Marcheggiani, Anton Frolov, Ivan Titov. 2017

111 citations recorded by the source corpus.

We introduce a simple and accurate neural model for dependency-based semantic role labeling. Our model predicts predicate-argument dependencies relying on states of a bidirectional LSTM encoder. The semantic role labeler achieves competitive performance on English, even without any kind of syntactic information and only using local inference. However, when automatically predicted part-of-speech tags are provided as input, it substantially outperforms all previous local models and approaches the best reported results on the English CoNLL-2009 dataset. We also consider Chinese, Czech and Spanish where our approach also achieves competitive results. Syntactic parsers are unreliable on out-of-domain data, so standard (i.e., syntactically-informed) SRL models are hindered when tested in this setting. Our syntax-agnostic model appears more robust, resulting in the best reported results on standard out-of-domain test sets.

Subfields: Artificial Intelligence, Natural Language Processing

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 Natural Language Processing

Citations in the corpus

The Natural Language Decathlon: Multitask Learning as Question Answering (2018, methodology): “(2008), but recent methods have demonstrated that it is not necessary to use syntactic information as additional input (Zhou and Xu, 2015; Marcheggiani et al., 2017).”
Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling (2017, methodology): “As expected though, our model does not outperform the syntax-agnostic model of Marcheggiani et al. (2017).”
Deep Semantic Role Labeling: What Works and What’s Next (2017, background): “Most recently, several successful LSTM-based architectures have achieved state-of-the-art results in English span-based SRL (Zhou and Xu, 2015), Chinese SRL (Wang et al., 2015), and dependency-based SRL (Marcheggiani et al., 2017) with little to no syntactic input.”
Linguistically-Informed Self-Attention for Semantic Role Labeling (2018, background): “, 2008), recently deep neural network architectures have surpassed syntacticallyinformed models (Zhou and Xu, 2015; Marcheggiani et al., 2017; He et al., 2017; Tan et al., 2018), achieving state-of-the art SRL performance with no explicit modeling of syntax.”
A Sequence-to-Sequence Model for Semantic Role Labeling (2018, background): “Marcheggiani et al. (2017) show that it is possible to construct a very accurate dependency-based SRL system without using any kind of explicit syntactic information.”
Jointly Predicting Predicates and Arguments in Neural Semantic Role Labeling (2018, background): “Recent high-performing SRL models (He et al., 2017; Marcheggiani et al., 2017; Tan et al., 2018) are BIO-taggers, labeling argument spans for a single predicate at a time (as shown in Figure 1).”
Deep Contextualized Self-training for Low Resource Dependency Parsing (2019, background): “Our focus task is dependency parsing, which is essential for many NLP tasks (Levy and Goldberg, 2014; Angeli et al., 2015; Toutanova et al., 2016; Hadiwinoto and Ng, 2017; Marcheggiani et al., 2017), but where self-training has typically failed (§ 2).”
Deep Semantic Role Labeling with Self-Attention (2017, background): “Recently, end-to-end models for SRL without syntactic inputs achieved promising results on this task (Zhou and Xu 2015; Marcheggiani, Frolov, and Titov 2017; He et al. 2017).”
Simple BERT Models for Relation Extraction and Semantic Role Labeling (2019, background): “State-of-the-art neural models for both tasks typically rely on lexical and syntactic features, such as part-of-speech tags (Marcheggiani et al., 2017), syntactic trees (Roth and Lapata, 2016; Zhang et al., 2018; Li et al., 2018), and global decoding constraints (Li et al., 2019).”