Keywords: Captioning, Language Generation, Modularized Method, Inverse of Language Parsing
TL;DR: a hierarchical and compositional way to generate captions
Abstract: Mainstream captioning models often follow a sequential structure to generate cap-
tions, leading to issues such as introduction of irrelevant semantics, lack of diversity
in the generated captions, and inadequate generalization performance. In this paper,
we present an alternative paradigm for image captioning, which factorizes the
captioning procedure into two stages: (1) extracting an explicit semantic represen-
tation from the given image; and (2) constructing the caption based on a recursive
compositional procedure in a bottom-up manner. Compared to conventional ones,
our paradigm better preserves the semantic content through an explicit factorization
of semantics and syntax. By using the compositional generation procedure, caption
construction follows a recursive structure, which naturally fits the properties of
human language. Moreover, the proposed compositional procedure requires less
data to train, generalizes better, and yields more diverse captions.
4 Replies
Loading