This is a brief summary of paper for me to study and arrange it, Jointly Learning Word Representations and Composition Functions Using Predicate-Argument Structures (Hashimoto et al., EMNLP 2014) I read and studied.

They focus on the dependecy embedding with predictate-arguemtne structure as follows:

Hashimoto et al., EMNLP 2014

In order for them to resolve the word disambiguation, they used POS information by combine word with POS taggging such as cause_NN.

Reference