A new thesis explores the challenges in creating personalized Conversational Information Access (CIA) systems. It proposes methods for extracting personal context through entity linking, generating personalized responses using large-scale conversational datasets, and evaluating system effectiveness with a new reference-free metric called FACE. The work aims to improve how CIA systems understand and adapt to individual user preferences. AI
IMPACT Introduces novel methods for personalizing conversational AI and evaluating its effectiveness.
RANK_REASON The cluster contains a research paper detailing new methods for conversational AI. [lever_c_demoted from research: ic=1 ai=1.0]
Read on arXiv cs.IR (Information Retrieval) →
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
