We train multi-task autoencoders on linguistic tasks and analyze the learned
hidden sentence representations. The representations change significantly when
translation and part-of-speech decoders are added. The more decoders a model
employs, the better it clusters sentences according to their syntactic
similarity, as the representation space becomes less entangled. We explore the
structure of the representation space by interpolating between sentences, which
yields interesting pseudo-English sentences, many of which have recognizable
syntactic structure. Lastly, we point out an interesting property of our
models: The difference-vector between two sentences can be added to change a
third sentence with similar features in a meaningful way.

训练多任务自动编码器进行语言任务，分析学习到的句子隐藏表示。加入翻译和词性解码器时，表示将显着改变。使用的解码器越多，模型根据句法相似性对句子进行聚类的效果越好。通过插值句子来探索表示空间的结构，得出很多有可识别句法结构的伪英语句子。最后，我们指出了模型的一个有意思的特性：两个句子之间的差分向量可以添加到第三个具有类似特征的句子中，以有意义的方式改变它。