all AI news
vec2text with Round-Trip Translations. (arXiv:2209.06792v1 [cs.CL])
cs.LG updates on arXiv.org arxiv.org
We investigate models that can generate arbitrary natural language text (e.g.
all English sentences) from a bounded, convex and well-behaved control space.
We call them universal vec2text models. Such models would allow making semantic
decisions in the vector space (e.g. via reinforcement learning) while the
natural language generation is handled by the vec2text model. We propose four
desired properties: universality, diversity, fluency, and semantic structure,
that such vec2text models should possess and we provide quantitative and
qualitative methods to assess …