Use of Query Similarity for Improving Presentation of News Verticals
نویسندگان
چکیده
Users often issue web queries related to current news events. For such queries, it is useful to predict the news intent automatically and highlight the news documents on the search result page. An example query would be “election results” issued during the time of elections. These highlighted displays are called news verticals. Prior work has proposed several features for predicting whether a query has news intent. However, most approaches treat each query individually. So on a given day, very similar queries can be assigned opposite predictions. In our work, we explore how a system can utilize query similarity information to improve the quality of news verticals along two dimensions—prediction and presentation. We show via a study of actual search traffic that the accuracy of predicting queries into newsworthy and not newsworthy categories can be improved using query similarity. Further, we present a method to identify a canonical variant for a newsworthy query such that using the canonical query would retrieve better results from the news backend to show in the display. Use of the canonical query also has the advantage of creating a consistent presentation of results for query variants related to the same news event.
منابع مشابه
Which Vertical Search Engines are Relevant? Understanding Vertical Relevance Assessments for Web Queries
Aggregating search results from a variety of heterogeneous sources, so-called verticals, such as news, image and video, into a single interface is a popular paradigm in web search. Current approaches that evaluate the effectiveness of aggregated search systems are based on rewarding systems that return highly relevant verticals for a given query, where this relevance is assessed under different...
متن کاملArabic News Articles Classification Using Vectorized-Cosine Based on Seed Documents
Besides for its own merits, text classification (TC) has become a cornerstone in many applications. Work presented here is part of and a pre-requisite for a project we have overtaken to create a corpus for the Arabic text process. It is an attempt to create modules automatically that would help speed up the process of classification for any text categorization task. It also serves as a tool for...
متن کاملA Methodology for Evaluating Aggregated Search Results
Aggregated search is the task of incorporating results from different specialized search services, or verticals, into Web search results. While most prior work focuses on deciding which verticals to present, the task of deciding where in the Web results to embed the vertical results has received less attention. We propose a methodology for evaluating an aggregated set of results. Our method eli...
متن کاملAggregated Search Result Diversification
Search result diversification has been effectively employed to tackle query ambiguity, particularly in the context of web search. However, ambiguity can manifest differently in different search verticals, with ambiguous queries spanning, e.g., multiple place names, content genres, or time periods. In this paper, we empirically investigate the need for diversity across four different verticals o...
متن کاملHow to Get the Same News from Different Language News Papers
This paper presents an ongoing work on identifying similarity between documents across News papers in different languages. Our aim is to identify similar documents for a given News or event as a query, across languages and make cross lingual search more accurate and easy. For example given an event or News in English, all the English news documents related to the query are retrieved as well as ...
متن کامل