Training Heterogeneous Features in Sequence to Sequence Tasks: Latent Enhanced Multi-filter Seq2Seq Model. (arXiv:2105.08840v2 [cs.CL] UPDATED)

In language processing, training data with extremely large variance may lead
to difficulty of language model's convergence. It is difficult for the network
parameters to adapt sentences with largely varied semantics or grammatical
structures. To resolve this problem, we introduce a model that concentrates the
each of the heterogeneous features in the input sentences. Build upon the
encoder-decoder architecture, we design a latent-enhanced multi-filter seq2seq
model (LEMS) that analyzes the input representations by introducing a latent
space transformation and clustering. …

arxiv features sequence to sequence training