Neural generation methods for task-oriented dialogue typically generate from
a meaning representation that is populated using a database of domain
information, such as a table of data describing a restaurant. While earlier
work focused solely on the semantic fidelity of outputs, recent work has
started to explore methods for controlling the style of the generated text
while simultaneously achieving semantic accuracy. Here we experiment with two
stylistic benchmark tasks, generating language that exhibits variation in
personality, and generating discourse contrast. We report a huge performance
improvement in both stylistic control and semantic accuracy over the state of
the art on both of these benchmarks. We test several different models and show
that putting stylistic conditioning in the decoder and eliminating the semantic
re-ranker used in earlier models results in more than 15 points higher BLEU for
Personality, with a reduction of semantic error to near zero. We also report an
improvement from .75 to .81 in controlling contrast and a reduction in semantic
error from 16% to 2%.

本研究旨在探索神经生成法如何同时实现语义准确度和文体控制，在两个文体基准任务中，通过在译码器中进行文体调节，消除先前模型中使用的语义再排序器，从而实现了语义误差降至接近零，并在 Personality 中实现了超过 15 个 BLEU 分数的巨大性能提升。在控制对比中还实现了从 0.75 到 0.81 的提升以及语义误差从 16% 降至 2%。