While neural machine translation (NMT) provides high-quality translation, it is still hard to interpret and analyze its behavior. We present an interactive interface for visualizing and intervening behavior of NMT, specifically concentrating on the behavior of beam search mechanism and attention component. The tool (1) visualizes search tree and attention and (2) provides interface to adjust se...

fuzzy cognitive maps (fcms) have successfully been applied in numerous domains to show the relations between essential components in complex systems. in this paper, a novel learning method is proposed to construct fcms based on historical data and by using meta-heuristic: genetic algorithm (ga), simulated annealing (sa), and tabu search (ts). implementation of the proposed method has demonstrat...

Users' search activity has been used as implicit feedback to model search interests and improve the performance of search systems. In search engines, this behavior usually takes the form of queries and result clicks. However, richer data on how people engage with search results can now be captured at scale, creating new opportunities to enhance search. In this poster we focus on one type of new...

Query data from search engines can provide many insights about the human behavior. Therefore, massive data resulting from human interactions may offer a new perspective on the behavior of the market. By analyzing Google query database for search terms, we present a method of analyzing large numbers of search queries to predict outcomes such as movie incomes. Our results illustrate the potential...

this paper considers the search problem, introduced by srivastava cite{sr}. this is a model discrimination problem. in the context of search linear models, discrimination ability of search designs has been studied by several researchers. some criteria have been developed to measure this capability, however, they are restricted in a sense of being able to work for searching only one possible non...

Falls among older people are a major public health issue. Increasing numbers of older people are accessing the internet for health-related information, including information on falls risk and prevention. However, we are aware of no study that has assessed the quality of such websites. Using techniques for conducting systematic literature reviews, we evaluated English-language websites offering ...

In mollusks, statocyst receptor cells (SRCs) interact with each other forming a neural network; their activity is determined by both the animal's orientation in the gravitational field and multimodal inputs. These two facts suggest that the function of the statocysts is not limited to sensing the animal's orientation. We studied the role of the statocysts in the organization of search motion du...

The advent of sponsored search advertising raises many interesting questions regarding consumer's behavior, seller's advertising strategy, and the ensuing market dynamics. Online markets are characterized by significant information asymmetries and consumers rely on a number of informational cues or signals to infer the seller's quality. Of the various quality signals, advertising and price have...

A motivational, self-regulatory conceptualization of job search was used to organize and investigate the relationships between personality, expectancies, self, social, motive, and biographical variables and individual differences in job search behavior and employment outcomes. Meta-analytic results indicated that all antecedent variables, except optimism, were significantly related to job searc...

We present a web-based diary study on location-based search behavior using a mobile search engine. To capture users' location-based search behavior in a ubiquitous setting, we use a web-based diary tool that collects users' detailed mobile search activity, their location and diary entries. This method enables us to capture users' explicit behavior (query made), their implicit intention (motivat...