Abstract
Actionable sentences are terms that, in the most basic sense, imply the necessity of taking a specific action. In Linguistic terms, they are steps to achieve an operation, often through the usage of action verbs. For example, the sentence, `Get your homework finished by tomorrow` qualifies as actionable since it demands a specific action (In this case, finishing homework) to be taken. In contrast, a simple sentence such as, `I like to play the guitar` does not qualify as an actionable phrase since it simply states a personal choice of the person instead of demanding a task to be finished. In this paper, the aim is to explore if Actionables can be extracted from raw text using Linguistic filters designed from scratch. These filters are specially catered to identifying actionable text using Transfer Learning as the lead role. Actionable Detection can be used in detecting emergency tasks during a crisis, Instruction accuracy for First aid and can also be used to make productivity tools like automatic ToDo list generators from conferences. To accomplish this, we use the Enron Email Dataset and apply our Linguistic filters on the cleaned textual data. We then use Transfer Learning with the Universal Sentence Encoder to train a model to classify whether a given string of raw text is actionable or not.
Abstract (translated)
URL
https://arxiv.org/abs/2210.16841
