Towards Incremental Transformers: An Empirical Analysis of Transformer Models for Incremental NLU

arXiv:2109.07364v2 Announce Type: replace
Abstract: Incremental processing allows interactive systems to respond based on partial inputs, which is a desirable property e.g. in dialogue agents. The currently popular Transformer architecture inherently processes sequences as a whole, abstracting away the notion of time. Recent work attempts to apply Transformers incrementally via restart-incrementality by repeatedly feeding, to an unchanged model, increasingly longer input prefixes to produce partial outputs. However, this approach is computationally costly and does not scale efficiently for long sequences. …

abstract agents analysis apply architecture arxiv cs.cl dialogue incremental inputs interactive nlu notion popular processes processing property systems transformer transformer architecture transformer models transformers type work