Learning with Weak Supervision for Email Intent Detection

Abstract

Email remains one of the most frequently used means of online communication. People spend 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.

Multimodal Marketing Intent Analysis for Effective Targeted Advertising

“…We are the first to study the problem systematically. Main focus of existing research is on human intent detection [10], [11], [12], [13], [14], which involves a variety of applications such as video search, intelligent vehicle, email conversation, E-commerce search, and so on. Some works focus on commercial intent detection [15], [16], [17], [18], [19], [20].…”

“…The relationship between the photographer's intent and the viewer's attention is explored to improve image analysis and understanding [11]. A self-paced learning mechanism is proposed for email intent detection by leveraging user actions as a source of weak supervision [12]. The Markov decision process is adopted to formulate the user intent prediction for user intent prediction in customer service bots [13].…”

Knodle: Modular Weakly Supervised Learning with PyTorch

“…However, in spam classification with only two classes (spam and not spam) there are rules covering both possible outcomes, and there is no need for unlabeled instances and filtering them out is reasonable. Current weak supervision frameworks provide only one of the two options: negative samples are either filtered out or included to the training dataset (Shu et al, 2020).…”

Weakly-supervised Text Classification Based on Keyword Graph

“…Weakly-supervised text classification (WTC) aims to use various weakly supervised signals to do text classification. Weak supervision signals used by existing methods includes external knowledge base (Gabrilovich et al, 2007;Chang et al, 2008;Song and Roth, 2014;Yin et al, 2019), keywords (Agichtein and Gravano, 2000;Riloff et al, 2003;Kuipers et al, 2006;Tao et al, 2015;Meng et al, 2018Meng et al, , 2019Meng et al, , 2020Mekala and Shang, 2020;Wang et al, 2021;Shen et al, 2021) and heuristics rules (Ratner et al, 2016(Ratner et al, , 2017Badene et al, 2019;Shu et al, 2020). In this paper, we focus on keyword-driven methods.…”