What Will Search Engines be Changed by NLP Advancements

Abstract

I think that the vision of a search engine is "Natural Search" with which users input his or her search intent in a natural way such as using natural language or an image and immediately obtains the desired accurate information which is concisely and comprehensibly expressed. During this process, NLP is undoubtedly one of the most crucial technologies. In the past, the search engine uses limited and shallow NLP technologies because NLP technology is not as mature as people have expected. In recent years, we have witnessed that NLP has made huge advances in various tasks such as semantic parser, question-answering, machine translation, machine reading comprehension and text generation. I think that now it is the time to consider applying these new technologies to a search engine to further improve the intelligence and naturalness of the search process. It is necessary to understand the new progress of NLP and their potential impact to a search engine. In this talk, I first provide an overview of advancements of methodology and technology in NLP filed in recent years. Then I will share my thoughts about the promising change of search engines brought by these new NLP technologies. I will further elaborate my thoughts on changing search engine with a set of intelligent question-answering techniques comprising semantic parser, question-answering and machine reading comprehension. Although these new promising NLP have rapidly brought meaningful change to a search engine, there are still many problems unsolved. As a conclusion, a list of the challenging topics will be proposed with my initial thoughts of solutions.