Email remains one of the most frequently used means of online communication. People spend a significant amount of time every day on emails to exchange information, manage tasks and schedule events. Previous work has studied different ways for improving email productivity by prioritizing emails, suggesting automatic replies or identifying intents to recommend appropriate actions. The problem has been mostly posed as a supervised learning problem where models of different complexities were proposed to classify an email message into a predefined taxonomy of intents or classes. The need for labeled data has always been one of the largest bottlenecks in training supervised models. This is especially the case for many real-world tasks, such as email intent classification, where large scale annotated examples are either hard to acquire or unavailable due to privacy or data access constraints. Email users often take actions in response to intents expressed in an email (e.g., setting up a meeting in response to an email with a scheduling request). Such actions can be inferred from user interaction logs. In this paper, we propose to leverage user actions as a source of weak supervision, in addition to a limited set of annotated examples, to detect intents in emails. We develop an end-to-end robust deep neural network model for email intent identification that leverages both clean annotated data and noisy weak supervision along with a self-paced learning mechanism. Extensive experiments on three different intent detection tasks show that our approach can effectively leverage the weakly supervised data to improve intent detection in emails.
Improved Out-of-Scope Intent Classification with Dual Encoding and Threshold-based Re-Classification
Technological University Dublin（都柏林理工大学）；Ireland’s Centre for Applied AI (CeADAR)（爱尔兰应用人工智能中心（CeADAR））；S Group（3S集团）；Huawei Research Centre（华为研究中心）；Amazon Alexa AI（亚马逊Alexa人工智能部门）
Bootstrapping Conversational Agents With Weak Supervision
IBM Watson（IBM沃森）；IBM Research AI（IBM研究院人工智能部门）
当今市场上的许多会话代理遵循标准的机器人开发框架，该框架需要训练意图分类器来识别用户输入。创建一组合适的训练样本的需求通常是开发过程中的瓶颈。在许多情况下，代理开发人员可以访问历史聊天日志，这些日志可以提供大量的训练样本。然而，用数十到数百个意图标记它们的成本通常会阻止充分利用这些聊天日志。在本文中，我们提出了一个框架称为\textit{search, label, and propagate}（SLP）的引导意图从现有的聊天日志使用弱监督。该框架通过使用搜索引擎查找示例，将数小时到数天的标记工作减少到几分钟的工作，然后依靠数据编程方法自动扩展标签。我们报告的用户研究，显示积极的用户反馈，这种新的方法来建立对话代理，并证明了使用数据编程自动标记的有效性。虽然该系统是为训练会话代理而开发的，但该框架在显着减少训练文本分类器的标记工作方面具有更广泛的应用。
DROID: Dual Representation for Out-of-Scope Intent Detection
School of Business, Maynooth University（梅诺特大学商学院）；Technological University Dublin（都柏林技术大学）；Huawei Research Centre（华为研究中心）；Amazon Alexa AI（亚马逊Alexa人工智能）
One Turn Too Late: Learning When to Intervene Against Multi-Turn Malicious Intent
Georgia Institute of Technology（佐治亚理工学院）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；UCSD（加州大学圣地亚哥分校）；National Taiwan University（台湾大学）；IBM Research（IBM研究院）；Virtue AI
Explicit State Tracking with Semi-Supervision for Neural Dialogue Generation
Fudan University（复旦大学）；National University of Singapore（新加坡国立大学）；King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）
对话生成的任务旨在自动提供响应给定先前的话语。跟踪对话状态是判断用户意图的一个重要环节。然而，\emph{expensive nature of state labeling}和\emph{weak interpretability}使得对话状态跟踪对于面向任务和非面向任务的对话生成都是具有挑战性的问题：对于在面向任务的对话中生成响应，状态跟踪通常从人工注释的语料库中学习，其中人工注释对于训练来说是昂贵的;对于在非面向任务的对话中生成响应，由于对话状态的数量不受限制，大多数现有工作忽略了显式状态跟踪。在本文中，我们提出了\emph{semi-supervised explicit dialogue state tracker}（SEDST）的神经对话生成。为此，我们的方法有两个核心成分：\emph{CopyFlowNet}和\emph{posterior regularization}。具体来说，我们提出了一个编码器-解码器架构，命名为\emph{CopyFlowNet}，表示一个明确的对话状态的概率分布在词汇空间。为了优化训练过程，我们采用后验正则化策略来整合间接监督。在任务型和非任务型对话语料库上进行的大量实验证明了该模型的有效性。此外，我们发现，我们提出的半监督对话状态跟踪器实现了国家的最先进的监督学习基线状态跟踪过程中的性能相当。
TaigiSpeech: A Low-Resource Real-World Speech Intent Dataset and Preliminary Results with Scalable Data Mining In-the-Wild
Massachusetts Institute of Technology, USA（麻省理工学院）；National Taiwan University, Taipei, Taiwan（国立台湾大学）；National Taiwan University Artificial Intelligence Center of Research Excellence, Taipei, Taiwan（国立台湾大学人工智能研究中心）；Academia Sinica, Taiwan（台湾“中央”研究院）；National Yang Ming Chiao Tung University, Taiwan（阳明交通大学）；Signal Analysis and Interpretation Laboratory (SAIL), University of Southern California, USA（信号分析与解释实验室（SAIL），南加州大学）
