Passage Feedback for News Tracking
نویسندگان
چکیده
We extend the event tracking task of Topic Detection and Tracking (TDT) to create a framework in which a user can highlight relevant passages in addition to specifying the relevance of documents. A dual framework of combined document and passage feedback improves performance over a state-of-the-art system without feedback by over 70% . Although annotators vary in the content and length of the passages marked for feedback, improvements in performance are consistent. We demonstrate how events in news follow certain trends over time, making passage feedback critical to event tracking.
منابع مشابه
A System for Adaptive Video News Story Tracking Based on the Earth Mover’s Distance
Every day there is an abundance of information broadcasted by all the news networks of the world. An automatic news story tracking system could watch all broadcasted news and track the stories in which we are interested in. In this thesis, a novel approach to news story tracking is investigated. We have designed a system for adaptive video news story tracking based on the Earth Mover’s Distance...
متن کاملADAPTIVE FUZZY OUTPUT FEEDBACK TRACKING CONTROL FOR A CLASS OF NONLINEAR TIME-VARYING DELAY SYSTEMS WITH UNKNOWN BACKLASH-LIKE HYSTERESIS
This paper considers the problem of adaptive output feedback tracking control for a class of nonstrict-feedback nonlinear systems with unknown time-varying delays and unknown backlash-like hysteresis. Fuzzy logic systems are used to estimate the unknown nonlinear functions. Based on the Lyapunov–Krasovskii method, the control scheme is constructed by using the backstepping and adaptive techniqu...
متن کاملVelocity Control of Electro Hydraulic Servo System by Tracking Method
This paper proposes an efficient Tracking method for velocity control of an electro-hydraulic servo system (EHSS) in the presence of flow nonlinearities and internal friction. The tracking method controller is a kind of feedback error learning structure. In the proposed method, the Feedback Error Learning (FEL) algorithm is used to control the velocity. There is no need to compute the system ja...
متن کاملEnhancement of Robust Tracking Performance via Switching Supervisory Adaptive Control
When the process is highly uncertain, even linear minimum phase systems must sacrifice desirable feedback control benefits to avoid an excessive ‘cost of feedback’, while preserving the robust stability. In this paper, the problem of supervisory based switching Quantitative Feedback Theory (QFT) control is proposed for the control of highly uncertain plants. According to this strategy, the unce...
متن کاملAutomatic Text Categorization Using Trend-Tracking Technique
In this paper, we propose a novel text categorization method using trendtracking technique. The method classies texts by tracking the transition of information in them. Therefore, it can deal especially well with texts whose content transits gradually with the passage of time, such as Internet news articles, newspaper articles, or web pages which are often updated. Experimental results show tha...
متن کامل