Tree-structured neural networks exploit valuable syntactic parse information
as they interpret the meanings of sentences. However, they suffer from two key
technical problems that make them slow and unwieldy for large-scale NLP tasks:
they can only operate on parsed sentences and they do not directly support
batched computation.

Source: A Fast Unified Model for Parsing and Sentence Understanding. (arXiv:1603.06021v1 [cs.CL]) – Natural Language Processing (NLP) News