Adaptive Convolution for Semantic Role Labeling
This work provides an incremental improvement in SRL performance for NLP researchers by more effectively leveraging syntactic information.
This paper addresses the challenge of effectively incorporating syntactic information into Semantic Role Labeling (SRL) by proposing adaptive convolution. This method uses input-specific filters, generated by a filter generation network, to focus on important syntactic features, leading to substantial performance improvements on the CoNLL-2009 dataset for both English and Chinese.
Semantic role labeling (SRL) aims at elaborating the meaning of a sentence by forming a predicate-argument structure. Recent researches depicted that the effective use of syntax can improve SRL performance. However, syntax is a complicated linguistic clue and is hard to be effectively applied in a downstream task like SRL. This work effectively encodes syntax using adaptive convolution which endows strong flexibility to existing convolutional networks. The existing CNNs may help in encoding a complicated structure like syntax for SRL, but it still has shortcomings. Contrary to traditional convolutional networks that use same filters for different inputs, adaptive convolution uses adaptively generated filters conditioned on syntactically informed inputs. We achieve this with the integration of a filter generation network which generates the input specific filters. This helps the model to focus on important syntactic features present inside the input, thus enlarging the gap between syntax-aware and syntax-agnostic SRL systems. We further study a hashing technique to compress the size of the filter generation network for SRL in terms of trainable parameters. Experiments on CoNLL-2009 dataset confirm that the proposed model substantially outperforms most previous SRL systems for both English and Chinese languages