Narrow Results

Collaborative filtering methods are widely accepted and used for item recommendation in various applications and domains. Their simplicity and ability to provide recommendations without the need for specific domain knowledge makes them utilized in both academic and industrial community. However, continuous dynamics of the system makes them vulnerable on different kind of changes, such as the change in user’s preferences or the appearance of new users and items in the system. It is particularly emphasized in user-based collaborative filtering recommendations which are based on both users and its nearest neighbor’s long-term profiles. In this work an approach is presented in order to recognize some of the changes and provide an upgraded model that provides improved performance. Such changes include deviations in user’s mean ratings, changes in neighbors’ similarities, as well as deviations from neighbors’ mean rating. For each of the proposed improvements a set of matching parameters are identified that form a long-term user’s profile. The performance of the proposed models compared to standard user-based collaborative filtering methods is evaluated in terms of prediction accuracy. The experimental results performed on real data set show sound improvement utilizing adjustment of deviations from user’s mean ratings and the neighbor’s similarities, as well as promising improvement with adjustment of neighbor’s mean ratings.

In order to support uniform access to heterogeneous temporal information, we introduce the concept of a temporal mediator. A temporal mediator consists of three components: (i) a repository for windowing functions and conversion functions, (ii) a time granularity thesaurus and (iii) a query interpreter. There are two types of windowing functions: one associates each time point to a set of tuples, and the other associates each tuple to a set of time points. A conversion function transforms information in terms of one time granularity into that in terms of another time granularity. The time granularity thesaurus stores the knowledge about time granularities (e.g., names of time granularities and relationships among them). Users pose queries using the windowing functions and in terms of desired time granularities. (A query language, which can be used to form such queries, is given in the paper.) To answer such a user query, the query interpreter first employs the windowing functions together with the time granularity thesaurus to retrieve needed temporal data from the underlying databases and then uses the time granularity thesaurus to select suitable conversion functions which convert the responses to the desired time granularities. Thus, a temporal mediator provides a simple interface that supports uniform accesses to heterogeneous temporal databases.

This paper presents an information system for Chinese Information Extraction from Financial news (CHIEF). The ultimate target of the system is to extract information concerning the occurrence time and places of the financial activities in the different companies from a local Hong Kong newspaper, namely (Tao Kung Pao). To facilitate event extraction purpose, two groups of templates were defined, i.e. the company related and company restructuring templates. They are used to select the desired information for each type of financial activities, such as (bankruptcy) or (merge). Each specific event is then represented using a frame-based knowledge structure. Two types of slots are embedded in each frame: they are the activity- and time-related slots. Based on these slots, multiple activities are interconnected according to their entity relations, temporal relations or the deduced relations. Effectively, CHIEF is a question-answering system designed for handling the company related queries, event based queries, temporal queries and complex queries in a finance domain.

This paper develops a Natural Language Processing method for extracting temporal information of events from news articles. The extraction process is based on the result of a morpho-syntactic analysis. The obtained results, which are a translation of morpho-syntactic sentences, are skimmed in order to identify temporal markers.

In our approach, we consider a specific description of events. Our approach is based on a methodology of temporal markers classes and on a contextual exploration method.

Our experimental results indicate that our approach is significant for extracting relevant event information. We have also achieved a system, called EXEV, on the basis of the proposed approach and have empirically verified its effectiveness. More specifically, EXEV system automatically extracts all information about events (paragraphs or sentences) from news articles and specifies more information about events: associations, locations, temporal settings, etc.

The system was tested on press articles and gives recall and precision more than 80%.

Deep convolutional neural networks (ConvNets) have become ubiquitous in computer vision owing to their success in visual recognition tasks on still images. This has encouraged a number of novel methods for video classification that have progressively improved over conventional handcrafted features. Existing CNN-based methods for action recognition typically train multiple streams to extract spatial and temporal characteristics and finally combine their prediction scores. However, they rely heavily on appearance and short-term temporal information. In this chapter, we present a new hierarchically aggregated ConvNet architecture that can more effectively deal with long-term dynamics present in the action videos. The proposed network takes a long-term video as input and exploits temporal information at multiple levels of the network hierarchy capturing more complex dynamics of the input sequence. This is enabled using special aggregation functions that combine information from multiple temporal segments via their feature maps. Detailed experiments show that our approach outperforms state-of-the-art methods significantly on UCF-101 and HMDB51 benchmark datasets.

In EDSS there have not only temporal data but also temporal knowledge. Temporal repression is a very important problem. This paper describes a simple and maneuverable model framework. It uses the interval algebra theory to reconstruct knowledge base, adopts the layered conception of case character factors to construct cases, and integrates temporal reasoning and cased-based reasoning. This framework can realize knowledge’s temporal properties and corresponding relation between the set of character factors and the set of rules. It implements temporal knowledge expression and reasoning and provides dependable proofs for decision-maker. The paper final target is trying to solve the knowledge temporal problem in dynamic decision-making environment and provides an applied platform for researchers.