Abstract
Semantic role labeling (SRL) is dedicated to recognizing the predicate-argument structure of a sentence. Previous studies have shown syntactic information has a remarkable contribution to SRL performance. However, such perception was challenged by a few recent neural SRL models which give impressive performance without a syntactic backbone. This paper intends to quantify the importance of syntactic information to dependency SRL in deep learning framework. We propose an enhanced argument labeling model companying with an extended korder argument pruning algorithm for effectively exploiting syntactic information. Our model achieves state-of-the-art results on the CoNLL-2008, 2009 benchmarks for both English and Chinese, showing the quantitative significance of syntax to neural SRL together with a thorough empirical survey over existing models.
Highlights
Semantic role labeling (SRL), namely semantic parsing, is a shallow semantic parsing task, which aims to recognize the predicate-argument structure of each predicate in a sentence, such as who did what to whom, where and when, etc
There are two formulizations for semantic predicate-argument structures, one is based on constituents, the other is based on dependencies. The latter proposed by the CoNLL-2008 shared task (Surdeanu et al, 2008) is called semantic dependency parsing, which annotates the heads of arguments rather than phrasal arguments
In order to quantitatively evaluate the contribution of syntax to SRL, we adopt the ratio between labeled F1 score for semantic dependencies (Sem-F1) and the labeled attachment score (LAS) for syntactic dependencies introduced by CoNLL2008 Shared Task1 as evaluation metric
Summary
Semantic role labeling (SRL), namely semantic parsing, is a shallow semantic parsing task, which aims to recognize the predicate-argument structure of each predicate in a sentence, such as who did what to whom, where and when, etc. We seek to identify arguments and label their semantic roles given a predicate. There are two formulizations for semantic predicate-argument structures, one is based on constituents (i.e., phrase or span), the other is based on dependencies. The latter proposed by the CoNLL-2008 shared task (Surdeanu et al, 2008) is called semantic dependency parsing, which annotates the heads of arguments rather than phrasal arguments. SRL is decomposed into multi-step classification subtasks in pipeline systems, consisting of predicate identification and disambiguation, argument identification and classification
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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
