Use of Time-Aware Language Model in Entity Driven Filtering System
Vincent Bouvier, Patrice Bellot · 2014
Tracking entities, so that new or important information about that entities are caught, is a real challenge and has many applica-tions (e.g., information monitoring, market-ing,...). We are interesting in how to repre-sent an entity profile to fulfill two purposes: 1. entity detection and disambiguation, 2. novelty and importance quantification. We propose an entity profile, which uses two language models. First, the Reference Language Model (RLM), which is mainly used for disambiguation. Second, we pro-pose a formalization of a Time-Aware Lan-guage Model, which is used for novelty de-tection. To rank documents, we propose a semi-supervised classification approach which uses meta-features computed on doc-uments using entity profiles and time series. 1