Unsupervised Translation via Hierarchical Anchoring: Functional Mapping of Places across Cities
Unsupervised Translation via Hierarchical Anchoring: Functional Mapping of Places across Cities
复制标题
DOI：
10.1145/3394486.3403335
复制
发表时间：
2020-07
期刊：
影响因子：
--
通讯作者：
T. Yabe;K. Tsubouchi;Toru Shimizu;Y. Sekimoto;S. Ukkusuri
中科院分区：
文献类型：
--
作者：
T. Yabe;K. Tsubouchi;Toru Shimizu;Y. Sekimoto;S. Ukkusuri
由于收集大规模并行数据集的困难，无监督翻译已成为自然语言处理（NLP）中的一项热门任务。在城市计算领域，通过循环神经网络使用人类移动模式生成的地点嵌入用于了解城市地区的功能。跨城市翻译地点嵌入使我们能够跨城市转移知识，这可用于各种下游任务，例如规划新商店位置。尽管取得了这些进步，但由于直接采用 NLP 中的神经机器翻译 (NMT) 方法（其中不同语言的词汇量相似），当前的方法无法跨不同规模的领域（例如东京到新泻）翻译位置嵌入。我们将此问题称为无监督翻译任务中的域不平衡问题。我们通过提出一种无监督翻译方法来解决这个问题，该方法通过利用跨不平衡域存在的常见层次结构来翻译嵌入。我们的方法的有效性是使用从 6 个不同规模的日本城市的手机数据生成的位置嵌入来测试的。使用土地利用数据的验证表明，使用分层锚点可以提高跨不平衡域的翻译准确性。我们的方法与输入数据类型无关，因此除了语言学和城市计算之外，还可以应用于各个领域的无监督翻译任务。
Unsupervised translation has become a popular task in natural language processing (NLP) due to difficulties in collecting large scale parallel datasets. In the urban computing field, place embeddings generated using human mobility patterns via recurrent neural networks are used to understand the functionality of urban areas. Translating place embeddings across cities allow us to transfer knowledge across cities, which may be used for various downstream tasks such as planning new store locations. Despite such advances, current methods fail to translate place embeddings across domains with different scales (e.g. Tokyo to Niigata), due to the straightforward adoption of neural machine translation (NMT) methods from NLP, where vocabulary sizes are similar across languages. We refer to this issue as the domain imbalance problem in unsupervised translation tasks. We address this problem by proposing an unsupervised translation method that translates embeddings by exploiting common hierarchical structures that exist across imbalanced domains. The effectiveness of our method is tested using place embeddings generated from mobile phone data in 6 Japanese cities of heterogeneous sizes. Validation using landuse data clarify that using hierarchical anchors improves the translation accuracy across imbalanced domains. Our method is agnostic to input data type, thus could be applied to unsupervised translation tasks in various fields in addition to linguistics and urban computing.