Dialogue summarization has recently garnered significant attention due to its wide range of applications. However, existing methods for summarizing dialogues are suboptimal because they do not take into account the inherent structure of dialogue and rely heavily on labeled data, which can lead to poor performance in new domains. In this work, we propose DIONYSUS (dynamic input optimization in pre-training for dialogue summarization), a pre-trained encoder-decoder model for summarizing dialogues in any new domain. To pre-train DIONYSUS, we create two pseudo summaries for each dialogue example: one is produced by a fine-tuned summarization model, and the other is a collection of dialogue turns that convey important information. We then choose one of these pseudo summaries based on the difference in information distribution across different types of dialogues. This selected pseudo summary serves as the objective for pre-training DIONYSUS using a self-supervised approach on a large dialogue corpus. Our experiments show that DIONYSUS outperforms existing methods on six datasets, as demonstrated by its ROUGE scores in zero-shot and few-shot settings.
translated by 谷歌翻译
Many efforts have been made to construct dialog systems for different types of conversations, such as task-oriented dialog (TOD) and open-domain dialog (ODD). To better mimic human-level conversations that usually fuse various dialog modes, it is essential to build a system that can effectively handle both TOD and ODD and access different knowledge sources. To address the lack of available data for the fused task, we propose a framework for automatically generating dialogues that combine knowledge-grounded ODDs and TODs in various settings. Additionally, we introduce a unified model PivotBot that is capable of appropriately adopting TOD and ODD modes and accessing different knowledge sources in order to effectively tackle the fused task. Evaluation results demonstrate the superior ability of the proposed model to switch seamlessly between TOD and ODD tasks.
translated by 谷歌翻译
深度学习模型推断是许多企业和科学发现过程中的关键服务。本文介绍了Ribbon,这是一种新颖的深度学习推理服务系统,符合两个相互竞争的目标:服务质量(QoS)目标和成本效益。功能区背后的关键思想是智能采用各种云计算实例(异质实例)来满足QoS目标并最大程度地节省成本。功能区设计了一种贝叶斯优化驱动的策略,该策略可帮助用户在云计算平台上为其模型推理服务需求构建最佳的异质实例集 - 并且,功能区展示了其优于使用均匀实例池的推理服务系统的优越性。功能区可为不同的学习模型节省多达16%的推理服务成本,包括新兴的深度学习建议系统模型和药物发现的启用模型。
translated by 谷歌翻译
对话式AI中的现有研究主要将面向任务的对话框(TOD)和问题答案(QA)视为单独的任务。为了构建可以完成用户任务和支持信息寻求信息的对话代理的目标,构建一个可以访问各种外部知识的系统,构建一个处理TOD和QA的系统非常重要。在这项工作中,我们提出了一项新任务,开放式TOD(OB-TOD),将TOD与QA任务相结合,并将外部知识源扩展到包括明确的知识源(例如Web)和隐式知识源(例如,例如,预训练的语言模型)。我们创建了一个新的数据集ob-multiwoz,在这里,我们在其中丰富了Tod会议,并使用类似QA的信息寻求基于外部知识的经验。我们提出了一个统一的模型Opera(开放式末端到端任务对话框),可以适当地访问明确和隐性的外部知识,以解决定义的任务。实验结果表明,与闭环基线相比,Opera的表现出色,并说明了两种知识类型的价值。
translated by 谷歌翻译
由于缺乏培训数据和异质知识来源,知识接地的对话系统是挑战的。由于培训数据中涵盖的有限主题,现有系统在不良主题上表现不佳。此外,异构知识源使系统概括到其他任务的系统,因为不同知识表示中的知识来源需要不同的知识编码器。为了解决这些挑战,我们呈现插头,将不同知识来源均匀化为知识接地的对话生成任务的统一知识来源的语言模型。插头在对话生成任务上进行预先培训,调节统一的基本知识表示。它可以通过一些培训示例概括到不同下游知识接地的对话一代任务。两个基准测试的实证评估表明,我们的模型越好跨越不同的知识接地任务。它可以在完全监督的设置下实现具有最先进的方法的可比性,并且显着优于零拍摄和少量拍摄设置中的其他方法。
translated by 谷歌翻译
建立一个社会智能代理人涉及许多挑战,其中一个是教导代理人以人类的价值交谈。然而,在对话系统的区域中仍然可以解读价值驱动的聊天聊天。大多数现有数据集重点关注致命的推理或社会规范建模。在这项工作中,我们提出了一个名为ValueNet的新的大型人类价值数据集,其中包含21,374个文本情景的人为态度。数据集在十维中组织,符合跨文化研究中的基本人类价值理论。我们进一步开发了ValueNet的基于变换器的值回归模型,以学习公用事业分配。综合实证结果表明,学习的价值模型可以使广泛的对话任务受益。例如,通过教授具有钢筋学习的生成代理和价值模型的奖励,我们的方法在个性化对话生成数据集中获得最先进的性能:Persona-Chat。具有额外特征的价值,现有的情感识别模型使得能够在上下文中捕捉丰富的人类情绪,这进一步提高了IncatheticDialogues数据集中的致力学响应生成性能。据我们所知,Valuenet是人类价值建模的第一个大型文本数据集,我们是第一个尝试将价值模型结合到情感智能对话系统中的人。数据集可在https://liang-qiu.github.io/valuenet/上获得。
translated by 谷歌翻译
对抗商业黑匣子语音平台的对抗攻击,包括云语音API和语音控制设备,直到近年来接受了很少的关注。目前的“黑匣子”攻击所有严重依赖于预测/置信度评分的知识,以加工有效的对抗示例,这可以通过服务提供商直观地捍卫,而不返回这些消息。在本文中,我们提出了在更实用和严格的情况下提出了两种新的对抗攻击。对于商业云演讲API,我们提出了一个决定的黑匣子逆势攻击,这些攻击是唯一的最终决定。在偶变中,我们将决策的AE发电作为一个不连续的大规模全局优化问题,并通过自适应地将该复杂问题自适应地分解成一组子问题并协同优化每个问题来解决它。我们的春天是一种齐全的所有方法,它在一个广泛的流行语音和扬声器识别API,包括谷歌,阿里巴巴,微软,腾讯,达到100%的攻击攻击速度100%的攻击率。 iflytek,和景东,表现出最先进的黑箱攻击。对于商业语音控制设备,我们提出了Ni-Occam,第一个非交互式物理对手攻击,而对手不需要查询Oracle并且无法访问其内部信息和培训数据。我们将对抗性攻击与模型反演攻击相结合,从而产生具有高可转换性的物理有效的音频AE,而无需与目标设备的任何交互。我们的实验结果表明,NI-Occam可以成功欺骗苹果Siri,Microsoft Cortana,Google Assistant,Iflytek和Amazon Echo,平均SRO为52%和SNR为9.65dB,对抗语音控制设备的非交互式物理攻击。
translated by 谷歌翻译
Large pre-trained language models have recently enabled open-ended generation frameworks (e.g., prompt-to-text NLG) to tackle a variety of tasks going beyond the traditional data-to-text generation. While this framework is more general, it is under-specified and often leads to a lack of controllability restricting their real-world usage. We propose a new grounded keys-to-text generation task: the task is to generate a factual description about an entity given a set of guiding keys, and grounding passages. To address this task, we introduce a new dataset, called EntDeGen. Inspired by recent QA-based evaluation measures, we propose an automatic metric, MAFE, for factual correctness of generated descriptions. Our EntDescriptor model is equipped with strong rankers to fetch helpful passages and generate entity descriptions. Experimental result shows a good correlation (60.14) between our proposed metric and human judgments of factuality. Our rankers significantly improved the factual correctness of generated descriptions (15.95% and 34.51% relative gains in recall and precision). Finally, our ablation study highlights the benefit of combining keys and groundings.
translated by 谷歌翻译
Diverse data formats and ontologies of task-oriented dialogue (TOD) datasets hinder us from developing general dialogue models that perform well on many datasets and studying knowledge transfer between datasets. To address this issue, we present ConvLab-3, a flexible dialogue system toolkit based on a unified TOD data format. In ConvLab-3, different datasets are transformed into one unified format and loaded by models in the same way. As a result, the cost of adapting a new model or dataset is significantly reduced. Compared to the previous releases of ConvLab (Lee et al., 2019b; Zhu et al., 2020b), ConvLab-3 allows developing dialogue systems with much more datasets and enhances the utility of the reinforcement learning (RL) toolkit for dialogue policies. To showcase the use of ConvLab-3 and inspire future work, we present a comprehensive study with various settings. We show the benefit of pre-training on other datasets for few-shot fine-tuning and RL, and encourage evaluating policy with diverse user simulators.
translated by 谷歌翻译
本文介绍了Z-Code ++,这是一种针对抽象文本摘要优化的新的预训练的语言模型。该模型使用三种技术扩展了艺术编码器模型的状态。首先,我们使用两阶段的预训练过程来改善模型在低资源摘要任务上的性能。该模型首先是使用文本语料库进行语言理解的预先培训的,然后在汇总语料库中不断预先培训,以进行基础文本生成。其次,我们用分离的注意力层代替编码器中的自我发项层,其中每个单词都使用两个向量分别代表其内容和位置。第三,我们使用融合编码器,这是一种以层次方式编码长序列的简单而有效的方法。 Z-Code ++在13个文本摘要任务中的9个跨5种语言中创建了新的艺术状态。我们的模型的参数有效,因为它的表现优于XSUM上600倍较大的Palm-540b,并且在Samsum上的易经的200倍GPT3-175B较大。在零射击和少量设置中,我们的模型大大优于竞争模型。
translated by 谷歌翻译