Personalized and Subjective approaches to Natural Language Processing

Projektbeschreibung

Revolutionäre anpassungsfähige und zugängliche Sprachtechnologie

Der zunehmende Einsatz von KI durch verschiedene Online- und Social-Media-Plattformen zur Moderation, Erkennung von Beleidigungen sowie Stimmungsanalyse hat es schwierig gemacht, diese Probleme wirksam anzugehen. Außerdem schränken die hohen Kosten und die Komplexität der Sprachtechnologie den Zugang für viele Einzelpersonen und Organisationen ein, was das Problem noch verschärft. Das vom Europäischen Forschungsrat finanzierte Projekt PERSONAE wird den Zugang zur Sprachtechnologie verbessern, indem es die Forschung zu subjektiven Aufgaben in der natürlichen Sprachverarbeitung (NLP) vorantreibt. Der Schwerpunkt liegt auf der Erkennung von missbräuchlicher Sprache und der Stimmungsanalyse aus der Perspektive des einzelnen Nutzers, was zu besseren NLP-Modellentwürfen führt. Darüber hinaus wird das Projekt auf der Grundlage dieser Forschung subjektive Sprachtechnologien entwickeln, die sich im Laufe der Zeit an die Bedürfnisse des Einzelnen anpassen können.

Ziel

My project, PERSONAE, will make language technology (LT) accessible and valuable to everyone. I will revolutionize research in subjective tasks in NLP such as abusive language detection and sentiment and emotion analysis by developing a new field called personal NLP, yielding new datasets, tasks, and algorithms. This new research area will explore subjective tasks from the perspective of the individual as information receiver, making users active actors in the creation of LTs instead of mere recipients. This will allow for a more tailored, effective approach to NLP model design, resulting in better models overall.

Each person has their own interests and preferences based on their background and experience. These factors impact their views of what makes them happy, angry, or depressed over time. Language technologies (LTs) can consider individual preferences. However, current research presumes a static view of subjectivity: that a single ground truth underlies subjective tasks such as abusive language detection, an assumption that lacks human variability and prevents universal access to LTs.

Language-based AI such as virtual assistants is widely available. But despite significant scientific advances, most LT applications are inaccessible to individuals and their public's opinion has become increasingly negative. GPT-3's 2020 release boosted business-oriented applications such as copywriting and chatbots, yet few that let people improve their lives—for example, by controlling what they see on social media. This gap becomes more pronounced for subjective tasks.

I will design subjective LTs that can be adapted by individuals at will over time. Based on an ambitious meta approach able to generalize from existing, disconnected work, PERSONAE will rely on fully personalizable privacy-aware algorithms that can be used by anyone. It will reveal benefits of LT far beyond those of existing systems, paving the way for future applications.