TEMPS: Temporal Sentence Embeddings for Temporal Information Retrieval
This work presents TEMPS (Temporal Embedding Model for Precise Search), a modular temporal branch that attaches to a frozen semantic retriever and trains on that signal, and introduces Temporal Textual Similarity (TTS), a task that measures how well two anchored texts align in time, independent of their topical similar...
Mourad Hassani, Julien Romero, Amel Bouzeghoub et al.
· 0 citations