Distributed representations of words encode lexical semantic information, but how is that information encoded in word embeddings? Focusing on the skip-gram with negative-sampling method, we show theoretically and experimentally that the squared norm of word embedding encodes the information gain defined by the Kullback-Leibler divergence of the co-occurrence distribution of a word to the unigram distribution of the corpus. Furthermore, through experiments on tasks of keyword extraction, hypernym prediction, and part-of-speech discrimination, we confirmed that the KL divergence and the squared norm of embedding work as a measure of the informativeness of a word provided that the bias caused by word frequency is adequately corrected.

Measuring the semantic similarity between two sentences is still an important task. The word mover's distance (WMD) computes the similarity via the optimal alignment between the sets of word embeddings. However, WMD does not utilize word order, making it difficult to distinguish sentences with large overlaps of similar words, even if they are semantically very different. Here, we attempt to improve WMD by incorporating the sentence structure represented by BERT's self-attention matrix (SAM). The proposed method is based on the Fused Gromov-Wasserstein distance, which simultaneously considers the similarity of the word embedding and the SAM for calculating the optimal transport between two sentences. Experiments on paraphrase identification and semantic textual similarity show that the proposed method improves WMD and its variants. Our code is available at https://github.com/ymgw55/WSMD.

对于监督分类问题，本文考虑通过使用观察到的协变量来估算查询的标签概率。众所周知的非参数内核更顺畅，并在查询周围的球上占据平均值的$ k $-n $-nnn）估算器，但特别是对于球的大半径偏向而渐近偏差。消除这种偏差，本地多项式回归（LPOR）和Multiscale $ K $ -NN（MS-$ K $ -NN）通过围绕查询周围的本地回归来学习偏置术语并将其推断给查询本身。然而，他们的理论最优性已经显示为无限数量的训练样本的限制。为了纠正具有较少观察的渐近偏差，本文提出了一种局部径向回归（LRR）及其逻辑回归变量，称为局部径向逻辑回归（LRLR），通过结合LPOS和MS-$ K $ -NN的优点。这个想法很简单：通过将径向距离作为解释变量将径向距离施加到观察标签的本地回归，然后将估计的标记概率推断为零距离。我们的数值实验包括日常股票指数的现实世界数据集，证明了LRLR胜过LPOR和MS $ K $ -NN。

It is well-known that typical word embedding methods such as Word2Vec and GloVe have the property that the meaning can be composed by adding up the embeddings (additive compositionality). Several theories have been proposed to explain additive compositionality, but the following questions remain unanswered: (Q1) The assumptions of those theories do not hold for the practical word embedding. (Q2) Ordinary additive compositionality can be seen as an AND operation of word meanings, but it is not well understood how other operations, such as OR and NOT, can be computed by the embeddings. We address these issues by the idea of frequency-weighted centering at its core. This paper proposes a post-processing method for bridging the gap between practical word embedding and the assumption of theory about additive compositionality as an answer to (Q1). It also gives a method for taking OR or NOT of the meaning by linear operation of word embedding as an answer to (Q2). Moreover, we confirm experimentally that the accuracy of AND operation, i.e., the ordinary additive compositionality, can be improved by our post-processing method (3.5x improvement in top-100 accuracy) and that OR and NOT operations can be performed correctly.

综合正电子发射断层扫描/磁共振成像（PET/MRI）扫描仪通过PET和形态信息促进了同时获得代谢信息，并使用MRI进行了高软组织对比度。尽管PET/MRI促进了捕获高精度融合图像，但其主要缺点可以归因于进行衰减校正时遇到的困难，这对于定量PET评估是必不可少的。合并后的宠物/MRI扫描需要从MRI中产生衰减 - 校正图，这是由于伽马射线衰减信息与MRI之间没有直接关系。尽管可以轻松地为头部和骨盆区域执行基于MRI的骨组织分割，但通过胸部CT生成来实现准确的骨骼分割仍然是一项艰巨的任务。这可以归因于胸部发生的呼吸和心脏运动，以及其解剖学上复杂的结构和相对较薄的骨皮质。本文提出了一种方法，可以通过使用独立于模态的邻域描述符（思维）添加结构性约束，从而最大程度地减少解剖结构变化，而无需人类注释，从而将结构性变化（MID）添加到可以转换不配对图像的生成对抗网络（GAN）中。在这项研究中获得的结果揭示了拟议的U-Gat-It +思维方法，以优于所有其他竞争方法。这项研究的发现暗示了可能在没有人类注释的情况下从胸部MRI中合成临床上可接受的CT图像的可能性，从而最大程度地减少了解剖结构的变化。