Towards Large-Scale Collaborative Planning: Answering High-Level Search Queries Using Human Computation
نویسندگان
چکیده
Behind every search query is a high-level mission that the user wants to accomplish. While current search engines can often provide relevant information in response to well-specified queries, they place the heavy burden of making a plan for achieving a mission on the user. We take the alternative approach of tackling users’ highlevel missions directly by introducing a human computation system that generates simple plans, by decomposing a mission into goals and retrieving search results tailored to each goal. Results show that our system is able to provide users with diverse, actionable search results and useful roadmaps for accomplishing their missions.
منابع مشابه
Anytime Query Answering in RDF through Evolutionary Algorithms
We present a technique for answering queries over RDF data through an evolutionary search algorithm, using fingerprinting and Bloom filters for rapid approximate evaluation of generated solutions. Our evolutionary approach has several advantages compared to traditional databasestyle query answering. First, the result quality increases monotonically and converges with each evolution, offering “a...
متن کاملMS MARCO: A Human Generated MAchine Reading COmprehension Dataset
This paper presents our recent work on the design and development of a new, large scale dataset, which we name MS MARCO, for MAchine Reading COmprehension. This new dataset is aimed to overcome a number of well-known weaknesses of previous publicly available datasets for the same task of reading comprehension and question answering. In MS MARCO, all questions are sampled from real anonymized us...
متن کاملModelling Relational Statistics With Bayes Nets (Poster Presentation SRL Workshop)
Class-level dependencies model general relational statistics over attributes of linked objects and links. Class-level relationships are important in themselves, and they support applications like policy making, strategic planning, and query optimization. An example of a class-level query is “what is the percentage of friendship pairs where both friends are women?”. To represent class-level stat...
متن کاملLarge-scale Computation of Distributional Similarities for Queries
We present a large-scale, data-driven approach to computing distributional similarity scores for queries. We contrast this to recent webbased techniques which either require the offline computation of complete phrase vectors, or an expensive on-line interaction with a search engine interface. Independent of the computational advantages of our approach, we show empirically that our technique is ...
متن کاملConsidering Production Planning in the Multi-period Inventory Routing Problem with Transshipment between Retailers
Generally, the inventory routing problem occurs in a supply chain where customers consider the supplier responsible for inventory replenishment. In this situation, the supplier finds the answer to questions regarding the time and quantity of delivery to the customer as well as the sequence of customers in the routes. Considering the effect of production decisions on answering these questions, t...
متن کامل