Universal Mobile Information Retrieval

Abstract

International audienceThe shift in human computer interaction from desktop computing to mobile interaction highly influences the needs for new designed interfaces. In this paper, we address the issue of searching for information on mobile devices, an area also known as Mobile Information Retrieval. In particular, we propose to summarize as much as possible the information retrieved by any search engine to allow universal access to information

Disambiguating Implicit Temporal Queries by Clustering Top Relevant Dates in Web Snippets

“…al. [11] show that standard collocation extraction strategies also fail compared to longest frequent substrings identification. As a consequence, multiword unit identification is done as in Zamir et.…”

“…al. [11], who define a numeric heuristic based on word left and right contexts distribution analysis. This metric is specifically tuned towards the tokenization process of Web snippets in order to overcome the problems faced by usual tokenizers, sentence splitters or part-of-speech taggers, which due to the specific structure of Web snippets, fail to correctly process this type of collection.…”

“…[17]. Due to space limitations, we do not detail this pre-processing step as it can easily be reproduced from [11] and [17], and it is commonly used in Web snippet processing. Furthermore, a simple rulebased model supported on regular expressions is used to extract explicit temporal dates satisfying certain specific explicit patterns (e.g., yyyy, yyyy-yyyy, yyyy/yyyy, mm/dd/yyyy, mm.dd.yyyy, dd/mm/yyyy and dd.mm/yyyy).…”

How Do Users Search the Mobile Web with a Clustering Interface?

“…This can be broken down into specific design challenges: how the category overview is presented and interacted with, when should the categories be shown, and which information to include in the category overview. Previous interface designs have proposed "category-driven" approaches to address the first challenge, whereby the list of category labels is provided as the initial results view (e.g., Carpineto et al, 2009a;De Luca & Nürnberger, 2005;Heimonen & Käki, 2007;Machado et al, 2009). The situational benefits of categories and the navigation issues caused by inconsistent labeling necessitate a rethink of the categorydriven approach.…”

Using ephemeral clustering and query logs to organize web image search results on mobile devices

“…Nevertheless, large number of clusters and imprecise names are the main reasons to avoid the use of web cluster retrieval on main search engines [9]. Ephemeral Clustering has been used for web search results classification and has shown good results in previous works for mobile applications, in which the number of obtained clusters and the cluster label are important factors to expedite the user interaction time expense in the retrieval process [15].…”