High-Order Low-Rank Tensors for Semantic Role Labeling

By Tao Lei, Yuan Zhang, Lluís Màrquez i Villodre, Alessandro Moschitti, Regina Barzilay. 2015

50 citations recorded by the source corpus.

This paper introduces a tensor-based approach to semantic role labeling (SRL). The motivation behind the approach is to automatically induce a compact feature representation for words and their relations, tailoring them to the task. In this sense, our dimensionality reduction method provides a clear alternative to the traditional feature engineering approach used in SRL. To capture meaningful interactions between the argument, predicate, their syntactic path and the corresponding role label, we compress each feature representation first to a lower dimensional space prior to assessing their interactions. This corresponds to using an overall cross-product feature representation and maintaining associated parameters as a four-way low-rank tensor. The tensor parameters are optimized for the SRL performance using standard online algorithms. Our tensor-based approach rivals the best performing system on the CoNLL-2009 shared task. In addition, we demonstrate that adding the representation tensor to a competitive tensorfree model yields 2% absolute increase in Fscore. 1

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling (2017, methodology): “…syntactic features within an MLP calculating potentials of a CRF model; Roth and Lapata (2016) who enriched standard features for SRL with LSTM representations of syntactic paths between arguments and predicates; Lei et al. (2015) who relied on low-rank tensor factorizations for modeling syntax.”
Spatial role labeling with convolutional neural networks (2015, methodology): “Future work in the area can thus leverage on advances within the general area of semantic role labeling [19, 28].”
Semantic Role Labeling with Neural Network Factors (2015, methodology): “Lei et al. (2015) employ low-rank tensor factorization to induce a compact representation of the full cross-product of atomic features; akin to this work, they represent semantic roles as real-valued vectors, but use a different scoring formulation for modeling potential arguments.”
A Simple and Accurate Syntax-Agnostic Neural Model for Dependency-based Semantic Role Labeling (2017, background): “Nevertheless, state-of-the-art methods for dependency-based SRL still heavily rely on syntactic features (Roth and Lapata, 2016; FitzGer-ald et al., 2015; Lei et al., 2015; Roth and Wood-a send, 2014; Swayamdipta et al., 2016).”
Neural Semantic Role Labeling with Dependency Path Embeddings (2016, methodology): “For instance, consider the sentence He had trouble raising funds and the analyses provided by four publicly available tools in Table 1 (mate-tools, Bj¨orkelund et al. (2010); mateplus, Roth and Woodsend (2014); TensorSRL, Lei et al. (2015); and easySRL, Lewis et al. (2015)).”