Learn More
Search and recommendation systems must include contextual information to effectively model users' interests. In this paper, we present a systematic study of the effectiveness of five variant sources of contextual information for user interest modeling. Post-query navigation and general browsing behaviors far outweigh direct search engine interaction as an(More)
This paper presents a new algorithm to automatically solve algebra word problems. Our algorithm solves a word problem via analyzing a hypothesis space containing all possible equation systems generated by assigning the numbers in the word problem into a set of equation system templates extracted from the training data. To obtain a robust decision surface,(More)
BACKGROUND Consumer use of mobile devices as health service delivery aids (mHealth) is growing, especially as smartphones become ubiquitous. However, questions remain as to how consumer traits, health perceptions, situational characteristics, and demographics may affect consumer mHealth usage intentions, assimilation, and channel preferences. OBJECTIVE We(More)
We introduce a method for evaluating the relevance of all visible components of a Web search results page, in the context of that results page. Contrary to Cranfield-style evaluation methods, our approach recognizes that a user's initial search interaction is with the result page produced by a search system, not the landing pages linked from it. Our key(More)
Whole page relevance defines how well the surface-level repre-sentation of all elements on a search result page and the corre-sponding holistic attributes of the presentation respond to users' information needs. We introduce a method for evaluating the whole-page relevance of Web search engine results pages. Our key contribution is that the method allows us(More)
In this paper, we investigate different usages of feature representations in the web person name disambiguation task which has been suffering from the mismatch of vocabulary and lack of clues in web environments. In literature , the latter receives less attention and remains more challenging. We explore the feature space in this task and argue that(More)
Most existing relation extraction models make predictions for each entity pair locally and individually, while ignoring implicit global clues available in the knowledge base, sometimes leading to conflicts among local predictions from different entity pairs. In this paper, we propose a joint inference framework that utilizes these global clues to resolve(More)
In this paper, we present an adaptive stereo video object segmentation algorithm based on depth and spatio-temporal information. First, the object is extracted from the left channel with a new algorithm, which consists of three steps: depth segmentation, adaptive change detection based on twice frame-difference, and edge modification. Then, an inverse(More)
A multi-agent learning system model is presented to solve the problems existing in the present remote learning system, such as the monotonous pattern and passive educating. Integrated with intelligent agent technology, the multi-agent learning system gives an agent capability description language, on the basis of which we suggest relevant personal grouping(More)