Abstract

Semantic role labeling (SRL) is one of the basic natural language processing (NLP) problems. To this date, most of the successful SRL systems were built on top of some form of parsing results (Koomen et al., 2005; Palmer et al., 2010; Pradhan et al., 2013), where pre-defined feature templates over the syntactic structure are used. The attempts of building an end-to-end SRL learning system without using parsing were less successful (Collobert et al., 2011). In this work, we propose to use deep bi-directional recurrent network as an end-to-end system for SRL. We take only original text information as input feature, without using any syntactic knowledge. The proposed algorithm for semantic role labeling was mainly evaluated on CoNLL-2005 shared task and achieved F1 score of 81.07. This result outperforms the previous state-of-the-art system from the combination of different parsing trees or models. We also obtained the same conclusion with F1 = 81.27 on CoNLL2012 shared task. As a result of simplicity, our model is also computationally efficient that the parsing speed is 6.7k tokens per second. Our analysis shows that our model is better at handling longer sentences than traditional models. And the latent variables of our model implicitly capture the syntactic structure of a sentence.

Highlights

  • Semantic role labeling (SRL) is a form of shallow semantic parsing whose goal is to discover the predicate-argument structure of each predicate in a given input sentence

  • SRL is useful as an intermediate step in a wide range of natural language processing (NLP) tasks, such as information extraction (Bastianelli et al, 2013), automatic document categorization (Persson et al, 2009) and questionanswering (Dan and Lapata, 2007; Surdeanu et al, 2003; Moschitti et al, 2003)

  • 2011) proposed a unified neural network architecture using word embedding and convolution. They applied their architecture on four standard NLP tasks: Part-Of-Speech tagging (POS), chunking (CHUNK), Named Entity Recognition (NER) and Semantic Role Labeling (SRL)

Read more

Summary

Introduction

Semantic role labeling (SRL) is a form of shallow semantic parsing whose goal is to discover the predicate-argument structure of each predicate in a given input sentence. The location of an argument on syntactic tree provides an intermediate tag for improving the performance. Combination of different syntactic parsers was proposed to address this problem, from both feature level and model level (Surdeanu et al, 2007; Koomen et al, 2005; Pradhan et al, 2005). 2011) proposed a unified neural network architecture using word embedding and convolution They applied their architecture on four standard NLP tasks: Part-Of-Speech tagging (POS), chunking (CHUNK), Named Entity Recognition (NER) and Semantic Role Labeling (SRL). They were able to reach the previous state-of-the-art performance on all these tasks except for SRL. We find the traditional syntactic information can be inferred from the learned representations

Related Work
Approaches
Pipeline
Data set
Network topology
Convolutional neural network
Word embedding
LSTM network
Analysis
Findings
Conclusion and Future work

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.