Структурированное внимание

AbstractDeep learning techniques are increasingly popular in the textual entailment task, overcoming the fragility of traditional discrete models with hard alignments and logics. In particular, the recently proposed attention models …...

Filtering target-irrelevant information through hierarchically refining hidden states has been demonstrated to be effective for obtaining in- formative representations. However, previous work simply relies on locally normalized at- tention without …...