Semantic Role Labeling with Neural Network Factors

Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 960–970, Lisbon, Portugal, 17-21 September 2015. c⃝2015 Association for Computational Linguistics. Semantic Role Labeling with Neural Network Factors Nicholas FitzGerald‡∗ Oscar Täckström† Kuzman Ganchev† Dipanjan Das† ‡Department of Computer Science and Engineering, University of Washington † Google, New York nfitz@cs.uw.edu {oscart,kuzman,dipanjand}@google.com Abstract We present a new method for semantic role labeling in which arguments and seman- tic 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 func- tions of a graphical model designed for the SRL task. We consider both local and structured learning methods and ob- tain strong results on standard PropBank and FrameNet corpora with a straightfor- ward product-of-experts model. We fur- ther show how the model can learn jointly from PropBank and FrameNet annotations to obtain additional improvements on the smaller FrameNet dataset. 1 Introduction Semantic role labeling (SRL) is the task of iden- tifying the semantic arguments of a predicate and labeling them with their semantic roles. A key chal- lenge in this task is sparsity of labeled data: a given predicate-role instance may only occur a handful of times in the training set. Most existing SRL systems model each semantic role as an atomic unit of meaning, ignoring finer-grained semantic similarity between roles that can be leveraged to share context between similar labels, both within and across annotation conventions. Low-dimensional embedding representations have been shown to be successful in overcoming sparsity and representing label similarity across a wide range of tasks (Weston et al., 2011; Sriku- mar and Manning, 2014; Hermann et al., 2014; Lei et al., 2015). In this paper, we present a new model for SRL that embeds candidate arguments and semantic roles (in context of a predicate frame) in a shared vector space. A feed-forward neural ∗Work carried out during an internship at Google. network is learned to capture correlations of the re- spective embedding dimensions to create argument and role representations. The similarity of these two representations, as measured by their dot prod- uct, is used to score possible roles for candidate arguments within a graphical model. This graphical model jointly models the assignment of semantic roles to all arguments of a predicate, subject to structural linguistic constraints. Our model has several advantages. Compared to linear multiclass classifiers used in prior work, vector embeddings of the predictions overcome the assumption of modeling each semantic role as a discrete label, thus capturing fine-grained label sim- ilarity. Moreover, since predictions and inputs are embedded in the same vector space, and features extracted from inputs and outputs are decoupled, our approach is amenable to joint learning of multi- ple annotation conventions, such as PropBank and FrameNet, in a single model. Finally, as with other neural network approaches, our model obviates the need to manually engineer feature conjunctions. Our underlying inference algorithm for SRL follows Täckström et al. (2015), who presented a dynamic program for structured …

Content truncated to 500 words