论文标题
T-Star:使用AMR图作为中间表示的真实样式转移
T-STAR: Truthful Style Transfer using AMR Graph as Intermediate Representation
论文作者
论文摘要
平行语料库在培训文本样式转移(TST)模型中不可用是一个非常具有挑战性但常见的情况。同样,TST模型隐含地需要保留内容,同时将源句子转换为目标样式。为了解决这些问题,通常会构建中间表示形式,该表示没有样式,同时仍保留源句子的含义。在这项工作中,我们将抽象意义表示图(AMR)图作为中间样式不可知表示的有用性。我们认为,诸如AMR之类的语义符号是中间表示的自然选择。因此,我们提出了T-Star:包括两个组件,文本到AMR编码器和AMR到文本解码器的模型。我们提出了几种建模改进,以增强生成的AMR的风格不可知性。据我们所知,T-Star是将AMR用作TST的中间表示的第一部作品。通过彻底的实验评估,我们表明T-Star通过平均更高的内容保存,并以可忽略不计的损失(约3%)的样式准确性来显着胜过最先进的技术技术。通过详细的人类评估和90,000个评级,我们还表明,与TST TST模型相比,T-Star的幻觉幅度降低了50%。
Unavailability of parallel corpora for training text style transfer (TST) models is a very challenging yet common scenario. Also, TST models implicitly need to preserve the content while transforming a source sentence into the target style. To tackle these problems, an intermediate representation is often constructed that is devoid of style while still preserving the meaning of the source sentence. In this work, we study the usefulness of Abstract Meaning Representation (AMR) graph as the intermediate style agnostic representation. We posit that semantic notations like AMR are a natural choice for an intermediate representation. Hence, we propose T-STAR: a model comprising of two components, text-to-AMR encoder and a AMR-to-text decoder. We propose several modeling improvements to enhance the style agnosticity of the generated AMR. To the best of our knowledge, T-STAR is the first work that uses AMR as an intermediate representation for TST. With thorough experimental evaluation we show T-STAR significantly outperforms state of the art techniques by achieving on an average 15.2% higher content preservation with negligible loss (3% approx.) in style accuracy. Through detailed human evaluation with 90,000 ratings, we also show that T-STAR has up to 50% lesser hallucinations compared to state of the art TST models.