论文标题
vec2sent：用自然语言生成的探测句子嵌入
Vec2Sent: Probing Sentence Embeddings with Natural Language Generation
论文作者
论文摘要
我们通过从它们的条件生成以检索基本离散句子的目的而从中产生的黑框句子嵌入。我们认为这是一种新的无监督探测任务，并表明它与下游任务性能很好地相关。我们还说明了来自不同编码者产生的语言的不同。我们采用我们的方法来生成句子嵌入的句子类比。
We introspect black-box sentence embeddings by conditionally generating from them with the objective to retrieve the underlying discrete sentence. We perceive of this as a new unsupervised probing task and show that it correlates well with downstream task performance. We also illustrate how the language generated from different encoders differs. We apply our approach to generate sentence analogies from sentence embeddings.
