论文标题
最近的邻居机器翻译
Nearest Neighbor Machine Translation
论文作者
论文摘要
我们介绍了$ k $ -neart-neegbor Machine Translation（$ K $ nn-MT），该示例在大型缓存示例上预测令牌，使用最近的邻居分类器，使用神经翻译模型的表示形式进行相似性搜索。这种方法不需要额外的培训和尺度，即可在测试时间直接访问数十亿个示例，从而产生了高度表达的模型，从而始终如一地改善许多设置的性能。只需添加最近的邻居搜索就可以通过1.5 BLEU改善最先进的德语翻译模型。 $ k $ nn-MT允许通过使用特定领域的数据存储将单个模型适应不同的域，从而在零拍传输上平均提高了9.2 BLEU的结果，并实现了新的最新结果 - 而无需对这些域进行培训。大型多语言模型也可以专门用于特定的语言对，并改善了3个BLEU，可以从英语转换为德语和中文。定性地，$ k $ nn-mt很容易解释；它结合了源和目标上下文以检索高度相关的示例。
We introduce $k$-nearest-neighbor machine translation ($k$NN-MT), which predicts tokens with a nearest neighbor classifier over a large datastore of cached examples, using representations from a neural translation model for similarity search. This approach requires no additional training and scales to give the decoder direct access to billions of examples at test time, resulting in a highly expressive model that consistently improves performance across many settings. Simply adding nearest neighbor search improves a state-of-the-art German-English translation model by 1.5 BLEU. $k$NN-MT allows a single model to be adapted to diverse domains by using a domain-specific datastore, improving results by an average of 9.2 BLEU over zero-shot transfer, and achieving new state-of-the-art results -- without training on these domains. A massively multilingual model can also be specialized for particular language pairs, with improvements of 3 BLEU for translating from English into German and Chinese. Qualitatively, $k$NN-MT is easily interpretable; it combines source and target context to retrieve highly relevant examples.
