Dynamic Compositionality in Recursive Neural Networks with Structure-aware Tag Representations
This work addresses a specific limitation in NLP models for researchers and practitioners, offering an incremental improvement over existing tree-structured approaches.
The authors tackled the problem of recursive neural networks ignoring syntactic tags by introducing a structure-aware tag representation to dynamically control composition functions, achieving superior or competitive performance on sentence-level tasks like sentiment analysis and natural language inference.
Most existing recursive neural network (RvNN) architectures utilize only the structure of parse trees, ignoring syntactic tags which are provided as by-products of parsing. We present a novel RvNN architecture that can provide dynamic compositionality by considering comprehensive syntactic information derived from both the structure and linguistic tags. Specifically, we introduce a structure-aware tag representation constructed by a separate tag-level tree-LSTM. With this, we can control the composition function of the existing word-level tree-LSTM by augmenting the representation as a supplementary input to the gate functions of the tree-LSTM. In extensive experiments, we show that models built upon the proposed architecture obtain superior or competitive performance on several sentence-level tasks such as sentiment analysis and natural language inference when compared against previous tree-structured models and other sophisticated neural models.