Structured search and query understandingĪ common candidate retrieval strategy is full-text search, which indexes free-text documents as bags of words stored in an inverted index using term statistics to generate relevance scores (e.g., the BM25 ranking function).
In what follows, we review prior approaches to both retrieval and ranking and show how, for all of their success, they still have shortcomings that LTR&R helps address. Where most existing retrieval models are static (deterministic), learning to retrieve is dynamic and leverages customer feedback.Ĭonsequently, we advocate an approach to learning to retrieve that uses contextual multiarmed bandits, a form of reinforcement learning that optimizes the trade-off between exploring new retrieval strategies and exploiting known ones, in order to minimize “regret”. More recently, we have extended the learning-to-rank approach to include retrieval, in what we are calling learning-to-rank-and-retrieve (LTR&R). If the best candidate is not in the candidate set, it doesn’t matter how good our ranking model is customers will not get what they want. However, these benefits apply only to the candidates selected during the retrieval phase. Models adapted from information retrieval deal well with noisy GPS input and can leverage map information.
0 kommentar(er)
