Morality in dialogue systems has raised great attention in research recently. A moral dialogue system could better connect users and enhance conversation engagement by gaining users' trust. In this paper, we propose a framework, MoralDial to train and evaluate moral dialogue systems. In our framework, we first explore the communication mechanisms of morality and resolve expressed morality into four sub-modules. The sub-modules indicate the roadmap for building a moral dialogue system. Based on that, we design a simple yet effective method: constructing moral discussions from Rules of Thumb (RoTs) between simulated specific users and the dialogue system. The constructed discussion consists of expressing, explaining, and revising the moral views in dialogue exchanges, which makes conversational models learn morality well in a natural manner. Furthermore, we propose a novel evaluation method in the framework. We evaluate the multiple aspects of morality by judging the relation between dialogue responses and RoTs in discussions, where the multifaceted nature of morality is particularly considered. Automatic and manual experiments demonstrate that our framework is promising to train and evaluate moral dialogue systems.

Level 5 Autonomous Driving, a technology that a fully automated vehicle (AV) requires no human intervention, has raised serious concerns on safety and stability before widespread use. The capability of understanding and predicting future motion trajectory of road objects can help AV plan a path that is safe and easy to control. In this paper, we propose a network architecture that parallelizes multiple convolutional neural network backbones and fuses features to make multi-mode trajectory prediction. In the 2020 ICRA Nuscene Prediction challenge, our model ranks 15th on the leaderboard across all teams.

Large pretrained language models can easily produce toxic or biased content, which is prohibitive for practical use. In order to detect such toxic generations, existing methods rely on templates, real-world data extraction, crowdsourcing workers, or automatic generation to construct adversarial contexts that are likely to induce toxic generations. However, what type of context is more likely to induce unsafe responses is still under-explored. In this paper, we identify that context toxicity and context category (e.g., \textit{profanity}, \textit{insult}, \textit{drugs}, etc.) are two important factors to cause safety issues in response generation. Hence, we propose a method called \emph{reverse generation} to construct adversarial contexts conditioned on a given response, with the flexibility to control category, toxicity level, and inductivity of the generated contexts. Via reverse generation, we augment the existing BAD dataset and construct a new dataset BAD+ which contains more than 120K diverse and highly inductive contexts in 12 categories. We test three popular pretrained dialogue models (Blender, DialoGPT, and Plato2) and find that BAD+ can largely expose their safety problems. Furthermore, we show that BAD+ can greatly enhance the safety of generation and reveal the key factors of safety improvement. Our code and dataset is available at \url{https://github.com/thu-coai/Reverse_Generation}.

Graph neural networks have achieved significant success in representation learning. However, the performance gains come at a cost; acquiring comprehensive labeled data for training can be prohibitively expensive. Active learning mitigates this issue by searching the unexplored data space and prioritizing the selection of data to maximize model's performance gain. In this paper, we propose a novel method SMARTQUERY, a framework to learn a graph neural network with very few labeled nodes using a hybrid uncertainty reduction function. This is achieved using two key steps: (a) design a multi-stage active graph learning framework by exploiting diverse explicit graph information and (b) introduce label propagation to efficiently exploit known labels to assess the implicit embedding information. Using a comprehensive set of experiments on three network datasets, we demonstrate the competitive performance of our method against state-of-the-arts on very few labeled data (up to 5 labeled nodes per class).

The rapid development of aspect-based sentiment analysis (ABSA) within recent decades shows great potential for real-world society. The current ABSA works, however, are mostly limited to the scenario of a single text piece, leaving the study in dialogue contexts unexplored. In this work, we introduce a novel task of conversational aspect-based sentiment quadruple analysis, namely DiaASQ, aiming to detect the sentiment quadruple of target-aspect-opinion-sentiment in a dialogue. DiaASQ bridges the gap between fine-grained sentiment analysis and conversational opinion mining. We manually construct a large-scale, high-quality Chinese dataset and also obtain the English version dataset via manual translation. We deliberately propose a neural model to benchmark the task. It advances in effectively performing end-to-end quadruple prediction and manages to incorporate rich dialogue-specific and discourse feature representations for better cross-utterance quadruple extraction. We finally point out several potential future works to facilitate the follow-up research of this new task. The DiaASQ data is open at https://github.com/unikcc/DiaASQ

Out-of-Domain (OOD) intent detection is important for practical dialog systems. To alleviate the issue of lacking OOD training samples, some works propose synthesizing pseudo OOD samples and directly assigning one-hot OOD labels to these pseudo samples. However, these one-hot labels introduce noises to the training process because some hard pseudo OOD samples may coincide with In-Domain (IND) intents. In this paper, we propose an adaptive soft pseudo labeling (ASoul) method that can estimate soft labels for pseudo OOD samples when training OOD detectors. Semantic connections between pseudo OOD samples and IND intents are captured using an embedding graph. A co-training framework is further introduced to produce resulting soft labels following the smoothness assumption, i.e., close samples are likely to have similar labels. Extensive experiments on three benchmark datasets show that ASoul consistently improves the OOD detection performance and outperforms various competitive baselines.

情绪引起的提取（ECPE）是情感原因分析的衍生子任务之一（ECA），与情感提取（EE）共享丰富的相关特征（EE）并引起提取（CE）。因此，EE和CE经常被用作更好的特征学习的辅助任务，通过先前的工作通过多任务学习（MTL）框架建模，以实现最新的ECPE结果。但是，现有的基于MTL的方法无法同时建模特定特征和之间的交互作用，或者遭受标签预测的不一致。在这项工作中，我们考虑通过使用新型A^2NET模型执行两种对齐机制来解决以上改善ECPE的挑战。我们首先提出一个功能任务对齐方式，以明确对特定的情感和特定特定功能和共享交互式特征进行建模。此外，还实施了任务跨度的对准，其中ECPE和EE和CE组合之间的标签距离被缩小了以获得更好的标签一致性。对基准的评估表明，我们的方法在所有ECA子任务上的表现都优于当前最佳性能系统。进一步的分析证明了我们提出的一致性机制对任务的重要性。

事件提取（EE）是信息提取的重要任务，该任务旨在从非结构化文本中提取结构化事件信息。大多数先前的工作都专注于提取平坦的事件，同时忽略重叠或嵌套的事件。多个重叠和嵌套EE的模型包括几个连续的阶段来提取事件触发器和参数，这些阶段患有错误传播。因此，我们设计了一种简单而有效的标记方案和模型，以将EE作为单词关系识别，称为oneee。触发器或参数单词之间的关系在一个阶段同时识别出并行网格标记，从而产生非常快的事件提取速度。该模型配备了自适应事件融合模块，以生成事件感知表示表示和距离感知的预测指标，以整合单词关系识别的相对距离信息，从经验上证明这是有效的机制。对3个重叠和嵌套的EE基准测试的实验，即少数FC，GENIA11和GENIA13，表明Oneee实现了最新的（SOTA）结果。此外，ONEEE的推理速度比相同条件下的基线的推理速度快，并且由于它支持平行推断，因此可以进一步改善。

具有终身学习能力（LL）能力的质量检查模型对于实用的质量检查应用很重要，据报道，基于架构的LL方法是这些模型的有效实现。但是，将以前的方法扩展到质量检查任务是不平凡的，因为它们要么需要在测试阶段访问任务身份，要么不会从看不见的任务中明确对样本进行模拟。在本文中，我们提出了Diana：一种基于动态体系结构的终生质量检查模型，该模型试图通过迅速增强的语言模型来学习一系列QA任务。戴安娜（Diana）使用四种类型的分层组织提示来捕获来自不同粒度的质量检查知识。具体而言，我们专门介绍任务级别的提示来捕获特定任务的知识，以保留高LL性能并维护实例级别的提示，以学习跨不同输入样本共享的知识，以提高模型的概括性能。此外，我们专用于单独的提示来明确建模未看到的任务，并引入一组及时的密钥向量，以促进任务之间的知识共享。广泛的实验表明，戴安娜（Diana）的表现优于最先进的终身质量检查模型，尤其是在处理看不见的任务时。

为了响应现有的对象检测算法，应用于复杂的火灾方案，检测准确性较差，速度缓慢和困难的部署。本文提出了轻巧的火灾检测算法，可实现速度和准确性的平衡。首先，骨干网络的最后一层被SEPVIT块取代，以增强骨干网络与全局信息的联系；其次，轻型BIFPN颈网旨在减轻模型，同时改善特征提取。第三，全球注意机制（GAM）融合到网络中，以使模型更加专注于全球维度特征。最后，我们使用Mish激活函数和SIOU损失来提高收敛速度并同时提高准确性。实验结果表明，与原始算法相比，Light-Yolov5将MAP提高3.3％，将参数数量减少27.1％，将计算减少19.1％，达到91.1的FPS。即使与最新的Yolov7微型相比，Light-Yolov5的地图也高6.8％，这显示了该算法的有效性。