Rethinking search

نویسندگان

چکیده

When experiencing an information need, users want to engage with a domain expert, but often turn retrieval system, such as search engine, instead. Classical systems do not answer needs directly, instead provide references (hopefully authoritative) answers. Successful question answering offer limited corpus created on-demand by human experts, which is neither timely nor scalable. Pre-trained language models, contrast, are capable of directly generating prose that may be responsive at present they dilettantes rather than experts -- have true understanding the world, prone hallucinating, and crucially incapable justifying their utterances referring supporting documents in were trained over. This paper examines how ideas from classical pre-trained models can synthesized evolved into truly deliver on promise expert advice.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Rethinking mobile search: towards casual, shared, social mobile search experiences

The mobile search space has witnessed phenomenal growth in recent years. As a result there has been a growing body of research aimed at understanding why and how mobile users search the Web via their handsets and how their mobile search experiences could be improved. However, much of this work has focused on addressing the many challenges of the mobile space. In this short position paper argue ...

متن کامل

In Common Sense - Rethinking Web Search Results

The World Wide Web is a rich annotation system which allows people to relate to documents and sites from different perspectives. People describe, comment, relate or mock other Web pages in the context of their document. This richness is currently not reflected in snippets presented by Web search engines, where a search result is represented by the text found in the Web document alone. This pape...

متن کامل

Rethinking Full-Text Search for Multi-lingual Databases

Textual fields are commonly used in databases and applications to capture details that are difficult to formalize—comments, notes, and product descriptions. With the rise of the web, users expect that databases be capable of searching these fields quickly and accurately in their native language. Fortunately, most modern database systems provide some form of full-text indexing of free text field...

متن کامل

Rethinking Online Monitoring Methods for Information Retrieval Systems: From Search Product to Search Process

Searching information retrieval systems is a highly interactive, iterative process that cannot be understood simply by comparing the output of a search session (the “search product”) to a query stated in advance. In this article, we examine evaluation goals and methods for studying information retrieval behavior, drawing examples from our own research and that of others. We limit our review to ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Sigir Forum

سال: 2021

ISSN: ['0163-5840', '1558-0229']

DOI: https://doi.org/10.1145/3476415.3476428