论文标题
保留损失的地方：生活在一起，结合在一起的邻居
Locality Preserving Loss: Neighbors that Live together, Align together
论文作者
论文摘要
我们提出了一个保留局部性损失（LPL），该损失改善了矢量空间嵌入之间的比对，同时分开了不相关的表示。鉴于两个预处理的嵌入歧管，LPL优化了一个模型来投射嵌入并保持其本地邻居，同时将一个歧管与另一个歧管对齐。这减少了在诸如跨语言对准之类的任务中对齐两者所需的数据集的整体大小。我们表明，基于LPL的输入矢量空间之间的对齐是正常化的，与基线相比，准确性更好，一致，尤其是当训练组的大小很小时。我们证明了LPL优化对齐方式对语义文本相似性（STS），自然语言推理（SNLI），多元类别的语言推断（MNLI）和跨语性单词Alignment（CLA）的有效性，显示一致的改进，在较低的资源设置中发现了比基线的16％改进。
We present a locality preserving loss (LPL) that improves the alignment between vector space embeddings while separating uncorrelated representations. Given two pretrained embedding manifolds, LPL optimizes a model to project an embedding and maintain its local neighborhood while aligning one manifold to another. This reduces the overall size of the dataset required to align the two in tasks such as cross-lingual word alignment. We show that the LPL-based alignment between input vector spaces acts as a regularizer, leading to better and consistent accuracy than the baseline, especially when the size of the training set is small. We demonstrate the effectiveness of LPL optimized alignment on semantic text similarity (STS), natural language inference (SNLI), multi-genre language inference (MNLI) and cross-lingual word alignment(CLA) showing consistent improvements, finding up to 16% improvement over our baseline in lower resource settings.
