论文标题
使用目标端文档级语言模型的神经机器翻译的上下文感知解码器
Context-aware Decoder for Neural Machine Translation using a Target-side Document-Level Language Model
论文作者
论文摘要
尽管已经提出了许多上下文感知的神经机器翻译模型来将上下文纳入翻译中，但大多数模型都是在句子级别对齐的并行文档上端到端训练的。由于只有少数域（和语言对）具有这样的文档级并行数据，因此我们无法在大多数域中执行准确的上下文感知翻译。因此，我们提出了一种简单的方法，可以通过将文档级的语言模型纳入解码器，将句子级翻译模型转变为上下文感知模型。我们的上下文感知的解码器仅建立在句子级的平行语料库和单语库中；因此，不需要文档级并行数据。在理论上的观点中，这项工作的核心部分是使用上下文和当前句子之间的点相互信息的上下文信息的新颖表示。我们通过评估\ textsc {bleu}和对比度测试的上下文感知翻译，通过三个语言，英语到法语，英语对俄语，俄语和日语的有效性。
Although many context-aware neural machine translation models have been proposed to incorporate contexts in translation, most of those models are trained end-to-end on parallel documents aligned in sentence-level. Because only a few domains (and language pairs) have such document-level parallel data, we cannot perform accurate context-aware translation in most domains. We therefore present a simple method to turn a sentence-level translation model into a context-aware model by incorporating a document-level language model into the decoder. Our context-aware decoder is built upon only a sentence-level parallel corpora and monolingual corpora; thus no document-level parallel data is needed. In a theoretical viewpoint, the core part of this work is the novel representation of contextual information using point-wise mutual information between context and the current sentence. We show the effectiveness of our approach in three language pairs, English to French, English to Russian, and Japanese to English, by evaluation in \textsc{bleu} and contrastive tests for context-aware translation.
