Learning to Match
Jun Xu, Zhengdong Lu, Tianqi Chen, Hang Li
The main tasks in many applications can be formalized as matching between heterogeneous objects, including search, recommendation, question answering, paraphrasing, and image retrieval. For example, search can be viewed as a problem of matching between a query and a document, and image retrieval can be viewed as a problem of matching between a text query and an image.
A variety of machine learning techniques have been developed for various matching tasks. We refer to them as 'learning to match'. We think that it is necessary and important to conduct research on learning to match. To generalize the techniques for matching developed in different applications, we can make better understanding on the problems, develop more powerful machine learning methodologies, and apply them to all the applications.
At Noah’s Ark Lab, we have invented learning to match techniques for document retrieval, recommendation, natural language processing, and image retrieval, as described below. Actually, the general view on learning to match has helped us a lot in the development of the technologies. Read more ...