Placeholder translation systems enable the users to specify how a specific phrase is translated in the output sentence. The system is trained to output special placeholder tokens, and the user-specified term is injected into the output through the context-free replacement of the placeholder token. However, this approach could result in ungrammatical sentences because it is often the case that the specified term needs to be inflected according to the context of the output, which is unknown before the translation. To address this problem, we propose a novel method of placeholder translation that can inflect specified terms according to the grammatical construction of the output sentence. We extend the sequence-to-sequence architecture with a character-level decoder that takes the lemma of a user-specified term and the words generated from the word-level decoder to output the correct inflected form of the lemma. We evaluate our approach with a Japanese-to-English translation task in the scientific writing domain, and show that our model can incorporate specified terms in the correct form more successfully than other comparable models.
翻译:占位符翻译系统可以让用户在输出句中指定一个特定短语是如何翻译的。 系统通过输出占位符符号来培训, 用户指定的术语会通过无上下文替换占位符符号的方式被注入输出中。 但是, 这种方法可能会导致非语法句句, 因为通常情况下, 指定的术语需要根据输出的上下文来表达, 而该输出在翻译之前并不为人知。 为了解决这个问题, 我们提出了一个新的占位符翻译方法, 可以根据输出句的语法构造来体现指定术语 。 我们扩展了排序到顺序的结构, 其字符级解码器将使用用户指定的术语的lemma, 以及从字级解码生成的单词, 以输出精选的 Lemma 。 我们用科学写域的日文到英文翻译任务来评估我们的方法, 并显示我们的模型可以在正确格式中比其他可比模型更成功地纳入指定术语 。