Collection and Analysis of Ground Truth Data for Query Intent
نویسندگان
چکیده
Search engines try to support people in finding information and locating services on the web. What people are looking for depends on their underlying intent and is described by the query they enter in the search engine. These queries are often short and ambiguous. This paper describes the collection of ground truth data for query intent. Participants were asked to label their own search queries according to what they hoped to find with that query. The data can be used to investigate the reliability of external human assessors and to train automatic classification models.
منابع مشابه
Analysis of users’ query reformulation behavior in Web with regard to Wholis-tic/analytic cognitive styles, Web experience, and search task type
Background and Aim: The basic aim of the present study is to investigate users’ query reformulation behavior with regard to wholistic-analytic cognitive styles, search task type, and experience variables in using the Web. Method: This study is an applied research using survey method. A total of 321 search queries were submitted by 44 users. Data collection tools were Riding’s Cognitive Style A...
متن کاملApplying a climatologically oriented GIS in comparison of TRMM estimated severe thunderstorm rainfalls with ground truth in Sydney metropolitan area
The main objective of the current research was comparison of severe thunderstorm rainfalls with TRMM data when flash flooding events observed in the Sydney Metropolitan Area (SMA) located in NSW, Australia. Severe Thunderstorm Rainfall Events have been first extracted from the severe storm archive of the Australian BOM, by induction of specific criteria. The corresponded derived dataset includ...
متن کاملA Ground Truth For Half A Million Musical Incipits
Musical incipits are short extracts of scores, taken from the beginning. The RISM A/II collection [6] contains about half a million of them. This large collection size makes a ground truth very interesting for the development of music retrieval methods, but at the same time makes it very difficult to establish one. Human experts cannot be expected to sift through half a million melodies to find...
متن کاملSimulation and C 4 I Data Collection in Support of Force Xxi Training
The U.S. Army’s Force XXI initiative provides automated C4I systems to commanders and their staffs at the brigade through corps echelons to increase situational awareness and support improved command and control decision making. These systems provide extensive automation support, including local area networks for data communications within command post structures and wide area communications li...
متن کاملTransportation distances and human perception of melodic similarity
• ABSTRACT This article describes how transportation distances such as the Earth Mover’s Distance can be used for measuring melodic similarity for notated music. We represent music notation as weighted point sets in a two-dimensional space of onset time and pitch. The Earth Mover’s Distance can then be used for comparing point sets by determining how much work it would take to convert one of th...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2012