Syntax Aware LSTM Model for Chinese Semantic Role Labeling
This work addresses semantic role labeling for Chinese language processing, presenting an incremental architectural innovation.
The paper tackles the problem of incorporating parsing information for Chinese semantic role labeling by proposing a Syntax Aware LSTM model that modifies its structure based on dependency parsing, achieving significant improvement over the state-of-the-art on CPB 1.0 with statistical significance (p<0.05).
As for semantic role labeling (SRL) task, when it comes to utilizing parsing information, both traditional methods and recent recurrent neural network (RNN) based methods use the feature engineering way. In this paper, we propose Syntax Aware Long Short Time Memory(SA-LSTM). The structure of SA-LSTM modifies according to dependency parsing information in order to model parsing information directly in an architecture engineering way instead of feature engineering way. We experimentally demonstrate that SA-LSTM gains more improvement from the model architecture. Furthermore, SA-LSTM outperforms the state-of-the-art on CPB 1.0 significantly according to Student t-test ($p<0.05$).