We study the training of Vision Transformers for semi-supervised image
classification. Transformers have recently demonstrated impressive performance
on a multitude of supervised learning tasks. Surprisingly, we show Vision
Transformers perform significantly worse than Convolutional Neural Networks
when only a small set of labeled data is available. Inspired by this
observation, we introduce a joint semi-supervised learning framework,
Semiformer, which contains a transformer stream, a convolutional stream and a
carefully designed fusion module for knowledge sharing between these streams.
The convolutional stream is trained on limited labeled data and further used to
generate pseudo labels to supervise the training of the transformer stream on
unlabeled data. Extensive experiments on ImageNet demonstrate that Semiformer
achieves 75.5% top-1 accuracy, outperforming the state-of-the-art by a clear
margin. In addition, we show, among other things, Semiformer is a general
framework that is compatible with most modern transformer and convolutional
neural architectures. Code is available at
this https URL

本文研究了视觉 Transformer 在半监督图像分类中的训练方法，通过引入一个联合半监督学习框架 Semiformer，实现了有标记数据与无标记数据的知识共享，从而取得了 ImageNet 数据集上 75.5% 的 top-1 准确率，成为同类方法中最具优势的方法之一。

半监督视觉 Transformer

Semi-Supervised Vision Transformers

Dialogue state tracking is a key part of a task-oriented dialogue system,
which estimates the user's goal at each turn of the dialogue. In this paper, we
propose the Point-Or-Generate Dialogue State Tracker (POGD). POGD solves the
dialogue state tracking task in two perspectives: 1) point out explicitly
expressed slot values from the user's utterance, and 2) generate implicitly
expressed ones based on slot-specific contexts. It also shares parameters
across all slots, which achieves knowledge sharing and gains scalability to
large-scale across-domain dialogues. Moreover, the training process of its
submodules is formulated as a multi-task learning procedure to further promote
its capability of generalization. Experiments show that POGD not only obtains
state-of-the-art results on both WoZ 2.0 and MultiWoZ 2.0 datasets but also has
good generalization on unseen values and new slots.

本文提出了 Point-Or-Generate Dialogue State Tracker (POGD)，它从两个角度解决对话状态跟踪任务，并在所有插槽之间共享参数以实现知识共享和可扩展性，其子模块的训练过程被制定为一个多任务学习过程以进一步提高其普适性。实验表明，POGD 不仅在 WoZ 2.0 和 MultiWoZ 2.0 数据集上获得了最先进的结果，而且对未知值和新插槽具有良好的泛化性。

对话状态追踪：分类还是生成？

Point or Generate Dialogue State Tracker

Many multi-domain neural machine translation (NMT) models achieve knowledge
transfer by enforcing one encoder to learn shared embedding across domains.
However, this design lacks adaptation to individual domains. To overcome this
limitation, we propose a novel multi-domain NMT model using individual modules
for each domain, on which we apply word-level, adaptive and layer-wise domain
mixing. We first observe that words in a sentence are often related to multiple
domains. Hence, we assume each word has a domain proportion, which indicates
its domain preference. Then word representations are obtained by mixing their
embedding in individual domains based on their domain proportions. We show this
can be achieved by carefully designing multi-head dot-product attention modules
for different domains, and eventually taking weighted averages of their
parameters by word-level layer-wise domain proportions. Through this, we can
achieve effective domain knowledge sharing, and capture fine-grained
domain-specific knowledge as well. Our experiments show that our proposed model
outperforms existing ones in several NMT tasks.

本篇论文提出了使用独立词向量模块和基于词级别注意力机制的领域混合方法来实现多领域神经机器翻译的知识共享和精细化领域特定知识获取，实验结果表明该模型在多项 NMT 任务中表现优秀。

基于词级自适应逐层领域混合的多领域神经机器翻译

Multi-Domain Neural Machine Translation with Word-Level Adaptive  Layer-wise Domain Mixing

In this paper we presents results of research about elderly users of Stack
Overflow (Question and Answer portal for programmers). They have different
roles, different main activities and different habits. They are an important
part of the community, as they tend to have higher reputation and they like to
share their knowledge. This is a great example of possible way of keeping
elderly people active and helpful for society.

研究了 Stack Overflow 中老年用户的不同角色、主要活动和习惯，他们是社区的重要组成部分，因为他们通常拥有更高的声誉并愿意分享知识，这为保持老年人积极和对社会有益做出了积极的示范。