A recent advance in monolingual dependency parsing is the idea of a treebank
embedding vector, which allows all treebanks for a particular language to be
used as training data while at the same time allowing the model to prefer
training data from one treebank over others and to select the preferred
treebank at test time. We build on this idea by 1) introducing a method to
predict a treebank vector for sentences that do not come from a treebank used
in training, and 2) exploring what happens when we move away from predefined
treebank embedding vectors during test time and instead devise tailored
interpolations. We show that 1) there are interpolated vectors that are
superior to the predefined ones, and 2) treebank vectors can be predicted with
sufficient accuracy, for nine out of ten test languages, to match the
performance of an oracle approach that knows the most suitable predefined
treebank embedding for the test set.

通过引入预测句子 treebank 向量的方法以及探索在测试时移离预定义的 treebank 嵌入向量并设计 tailored 的插值方法，本研究在 monolingual dependency parsing 领域对 treebank embedding vector 的进一步改进进行了研究，并表明插值向量优于预定义的向量，对于十种语言中的九种测试语言，可以预测 treebank 向量以匹配 oracle 方法的性能。