Bridging Emoji Mashup and Lexical Composition

With the advent of Emojis in online text messages, large efforts have been made to
build Emoji Mashup System (EMS). EMS takes two separate emojis as input and
generates a new one that combines the two. Existing EMSs only leverage on the
visual information and forgo rich semantic information in the text. In this proposal,
we call efforts to bridge EMS and Lexical Composition (LC). LC is a classic NLP
tasks that investigate the meaning shift, implicit meaning, or both when combining
two words together. Hence by concept, LC and EMS are a pair of twins that both
combine/mashup words/emojis. We call efforts to bring empirical evidence that
how LC may benefit EMS from an NLP perspective.