论文标题
使用bitext的示例性控制和翻译
Exemplar-Controllable Paraphrasing and Translation using Bitext
论文作者
论文摘要
大多数基于示例性的句法释义生成的工作都依赖于自动构建的大规模释义数据集，这些数据集的创建成本很高。我们通过对先前工作的模型进行调整，以便能够仅从双语文本（bitext）学习来避开这一先决条件。尽管仅使用bitext进行训练，并且在接近零射的条件下，我们提出的单个模型可以执行四个任务：以两种语言的方式进行释义，并以两个语言方向的方式进行受控的机器翻译。为了定量评估这些任务，我们创建了三个新颖的评估数据集。我们的实验结果表明，我们的模型在受控的机器翻译上获得了受控释义的产生和强劲性能的竞争结果。分析表明，我们的模型学会在其潜在表示中删除语义和语法，但仍然遭受语义漂移的困扰。
Most prior work on exemplar-based syntactically controlled paraphrase generation relies on automatically-constructed large-scale paraphrase datasets, which are costly to create. We sidestep this prerequisite by adapting models from prior work to be able to learn solely from bilingual text (bitext). Despite only using bitext for training, and in near zero-shot conditions, our single proposed model can perform four tasks: controlled paraphrase generation in both languages and controlled machine translation in both language directions. To evaluate these tasks quantitatively, we create three novel evaluation datasets. Our experimental results show that our models achieve competitive results on controlled paraphrase generation and strong performance on controlled machine translation. Analysis shows that our models learn to disentangle semantics and syntax in their latent representations, but still suffer from semantic drift.
