Sentence Encoding with Tree-constrained Relation Networks
arXiv: Computation and Language, Volume abs/1811.10475, 2018.
The meaning of a sentence is a function of the relations that hold between its words. We instantiate this relational view of semantics in a series of neural models based on variants of relation networks (RNs) which represent a set of objects (for us, words forming a sentence) in terms of representations of pairs of objects. We propose two...More
PPT (Upload PPT)