Given a document in a source language, cross-lingual summarization (CLS) aims at generating a concise summary in a different target language. Unlike monolingual summarization (MS), naturally occurring source-language documents paired with target-language summaries are rare. To collect large-scale CLS samples, existing datasets typically involve translation in their creation. However, the translated text is distinguished from the text originally written in that language, i.e., translationese. Though many efforts have been devoted to CLS, none of them notice the phenomenon of translationese. In this paper, we first confirm that the different approaches to constructing CLS datasets will lead to different degrees of translationese. Then we design systematic experiments to investigate how translationese affects CLS model evaluation and performance when it appears in source documents or target summaries. In detail, we find that (1) the translationese in documents or summaries of test sets might lead to the discrepancy between human judgment and automatic evaluation; (2) the translationese in training sets would harm model performance in the real scene; (3) though machine-translated documents involve translationese, they are very useful for building CLS systems on low-resource languages under specific training strategies. Furthermore, we give suggestions for future CLS research including dataset and model developments. We hope that our work could let researchers notice the phenomenon of translationese in CLS and take it into account in the future.

Cross-Lingual Summarization (CLS) aims at generating summaries in one language for the given documents in another language. CLS has attracted wide research attention due to its practical significance in the multi-lingual world. Though great contributions have been made, existing CLS works typically focus on short documents, such as news articles, short dialogues and guides. Different from these short texts, long documents such as academic articles and business reports usually discuss complicated subjects and consist of thousands of words, making them non-trivial to process and summarize. To promote CLS research on long documents, we construct Perseus, the first long-document CLS dataset which collects about 94K Chinese scientific documents paired with English summaries. The average length of documents in Perseus is more than two thousand tokens. As a preliminary study on long-document CLS, we build and evaluate various CLS baselines, including pipeline and end-to-end methods. Experimental results on Perseus show the superiority of the end-to-end baseline, outperforming the strong pipeline models equipped with sophisticated machine translation systems. Furthermore, to provide a deeper understanding, we manually analyze the model outputs and discuss specific challenges faced by current approaches. We hope that our work could benchmark long-document CLS and benefit future studies.

与外部知识的接地对话系统是提高响应质量的一种有希望的方法。大多数现有的作品采用知识图（KGS）作为外部资源，关注对话的最后一句话中实体的贡献，以了解上下文理解和响应。然而，在多转变环境中隐含的知识与公斤关系之间的过渡规律之间的相关性是不足的。为此，我们提出了一个关系过渡意识知识的对话生成模型（RT-KGD）。具体而言，受到人类对话潜在逻辑的启发，我们的模型将对话级别的关系过渡规律与转向级实体语义信息相结合。以这种方式，知识之间的相互作用被认为是产生丰富的线索，以预测适当的知识并产生相干响应。自动评估和手动评估的实验结果表明，我们的模型表现优于最先进的基准。

跨语性摘要是用一种语言（例如英语）以不同语言（例如中文）生成一种语言（例如英语）的摘要。在全球化背景下，这项任务吸引了计算语言学界的越来越多的关注。然而，对于这项任务仍然缺乏全面的审查。因此，我们在该领域的数据集，方法和挑战上介绍了第一个系统的批判性审查。具体而言，我们分别根据不同的构造方法和解决方案范例仔细组织现有的数据集和方法。对于每种类型的数据集或方法，我们彻底介绍并总结了以前的努力，并将它们相互比较以提供更深入的分析。最后，我们还讨论了有希望的方向，并提供了我们的思想，以促进未来的研究。这项调查适用于跨语性摘要的初学者和专家，我们希望它将成为起点，也可以为对该领域感兴趣的研究人员和工程师提供新的想法。

Recent years have witnessed the resurgence of knowledge engineering which is featured by the fast growth of knowledge graphs. However, most of existing knowledge graphs are represented with pure symbols, which hurts the machine's capability to understand the real world. The multi-modalization of knowledge graphs is an inevitable key step towards the realization of human-level machine intelligence. The results of this endeavor are Multi-modal Knowledge Graphs (MMKGs). In this survey on MMKGs constructed by texts and images, we first give definitions of MMKGs, followed with the preliminaries on multi-modal tasks and techniques. We then systematically review the challenges, progresses and opportunities on the construction and application of MMKGs respectively, with detailed analyses of the strength and weakness of different solutions. We finalize this survey with open research problems relevant to MMKGs.

体育比赛摘要旨在从实时评论产生体育新闻。但是，现有数据集全部通过自动收集和清洁过程构建，导致大量噪音。此外，目前的作品忽视了现场评论和体育新闻之间的知识差距，这限制了体育比赛摘要的表现。在本文中，我们介绍了K-Sportssum，一个具有两个特征的新数据集：（1）K-Sportssum从大规模游戏中收集大量数据。它有7,854个评论新闻性对。为了提高质量，K-Sportssum采用手动清洁过程; （2）与现有数据集不同，为了缩小知识缺口，K-Sportssum进一步提供了一个大型知识语料库，其中包含523名运动队和14,724名体育运动者的信息。此外，我们还介绍了一个知识增强的摘要，它利用实时评论和知识来生成体育新闻。关于K-Sportssum和Sportssum数据集的广泛实验表明，我们的模型实现了新的最先进的表演。定性分析和人类研究进一步验证我们的模型产生更具信息丰富的体育新闻。

我们研究了GaN调理问题，其目标是使用标记数据将普雷雷尼的无条件GaN转换为条件GaN。我们首先识别并分析这一问题的三种方法 - 从头开始​​，微调和输入重新编程的条件GaN培训。我们的分析表明，当标记数据的数量很小时，输入重新编程执行最佳。通过稀缺标记数据的现实世界情景，我们专注于输入重编程方法，并仔细分析现有算法。在识别出先前输入重新编程方法的一些关键问题之后，我们提出了一种名为INREP +的新算法。我们的算法INREP +解决了现有问题，具有可逆性神经网络的新颖用途和正面未标记（PU）学习。通过广泛的实验，我们表明Inrep +优于所有现有方法，特别是当标签信息稀缺，嘈杂和/或不平衡时。例如，对于用1％标记数据调节CiFar10 GaN的任务，Inrep +实现了82.13的平均峰值，而第二个最佳方法达到114.51。

In this paper, we propose a robust 3D detector, named Cross Modal Transformer (CMT), for end-to-end 3D multi-modal detection. Without explicit view transformation, CMT takes the image and point clouds tokens as inputs and directly outputs accurate 3D bounding boxes. The spatial alignment of multi-modal tokens is performed implicitly, by encoding the 3D points into multi-modal features. The core design of CMT is quite simple while its performance is impressive. CMT obtains 73.0% NDS on nuScenes benchmark. Moreover, CMT has a strong robustness even if the LiDAR is missing. Code will be released at https://github.com/junjie18/CMT.

Dataset distillation has emerged as a prominent technique to improve data efficiency when training machine learning models. It encapsulates the knowledge from a large dataset into a smaller synthetic dataset. A model trained on this smaller distilled dataset can attain comparable performance to a model trained on the original training dataset. However, the existing dataset distillation techniques mainly aim at achieving the best trade-off between resource usage efficiency and model utility. The security risks stemming from them have not been explored. This study performs the first backdoor attack against the models trained on the data distilled by dataset distillation models in the image domain. Concretely, we inject triggers into the synthetic data during the distillation procedure rather than during the model training stage, where all previous attacks are performed. We propose two types of backdoor attacks, namely NAIVEATTACK and DOORPING. NAIVEATTACK simply adds triggers to the raw data at the initial distillation phase, while DOORPING iteratively updates the triggers during the entire distillation procedure. We conduct extensive evaluations on multiple datasets, architectures, and dataset distillation techniques. Empirical evaluation shows that NAIVEATTACK achieves decent attack success rate (ASR) scores in some cases, while DOORPING reaches higher ASR scores (close to 1.0) in all cases. Furthermore, we conduct a comprehensive ablation study to analyze the factors that may affect the attack performance. Finally, we evaluate multiple defense mechanisms against our backdoor attacks and show that our attacks can practically circumvent these defense mechanisms.

Automatic music generation with artificial intelligence typically requires a large amount of data which is hard to obtain for many less common genres and musical instruments. To tackle this issue, we present ongoing work and preliminary findings on the possibility for deep models to transfer knowledge from language to music, by finetuning large language models pre-trained on a massive text corpus on only hundreds of MIDI files of drum performances. We show that by doing so, one of the largest, state-of-the-art models (GPT3) is capable of generating reasonable drum grooves, while models that are not pre-trained (Transformer) shows no such ability beyond naive repetition. Evaluating generated music is a challenging task, more so is evaluating drum grooves with little precedence in literature. Hence, we propose a tailored structural evaluation method and analyze drum grooves produced by GPT3 compared to those played by human professionals, exposing the strengths and weaknesses of such generation by language-to-music transfer. Our findings suggest that language-to-music transfer learning with large language models is viable and promising.