SYSTEMS AND METHODS FOR A TRANSFORMER NETWORK WITH TREE-BASED ATTENTION FOR NATURAL LANGUAGE PROCESSING

Embodiments described herein provide an attention-based tree encoding mechanism. Specifically, the attention layer receives as input the pre-parsed constituency tree of a sentence and the lower-layer representations of all nodes. The attention layer then performs upward accumulation to encode the tree structure from leaves to the root in a bottom-up fashion. Afterwards, weighted aggregation is used to compute the final representations of non-terminal nodes.