Sciweavers

AAAI
2015
8 years 8 months ago
Learning Greedy Policies for the Easy-First Framework
Easy-first, a search-based structured prediction approach, has been applied to many NLP tasks including dependency parsing and coreference resolution. This approach employs a lea...
Jun Xie, Chao Ma, Janardhan Rao Doppa, Prashanth M...
AAAI
2015
8 years 8 months ago
Balanced Trade Reduction for Dual-Role Exchange Markets
We consider dual-role exchange markets, where traders can offer to both buy and sell the same commodity in the exchange but, if they transact, they can only be either a buyer or a...
Dengji Zhao, Sarvapali D. Ramchurn, Enrico H. Gerd...
AAAI
2015
8 years 8 months ago
Towards Cognitive Automation of Data Science
A Data Scientist typically performs a number of tedious and time-consuming steps to derive insight from a raw data set. The process usually starts with data ingestion, cleaning, a...
Alain Biem, Maria Butrico, Mark Feblowitz, Tim Kli...
AAAI
2015
8 years 8 months ago
Self-Paced Curriculum Learning
Curriculum learning (CL) or self-paced learning (SPL) represents a recently proposed learning regime inspired by the learning process of humans and animals that gradually proceeds...
Lu Jiang, Deyu Meng, Qian Zhao, Shiguang Shan, Ale...
AAAI
2015
8 years 8 months ago
Unsupervised Word Sense Disambiguation Using Markov Random Field and Dependency Parser
Word Sense Disambiguation is a difficult problem to solve in the unsupervised setting. This is because in this setting inference becomes more dependent on the interplay between d...
Devendra Singh Chaplot, Pushpak Bhattacharyya, Ash...
AAAI
2015
8 years 8 months ago
Approximate Linear Programming for Constrained Partially Observable Markov Decision Processes
In many situations, it is desirable to optimize a sequence of decisions by maximizing a primary objective while respecting some constraints with respect to secondary objectives. S...
Pascal Poupart, Aarti Malhotra, Pei Pei, Kee-Eung ...
AAAI
2015
8 years 8 months ago
Robust Image Sentiment Analysis Using Progressively Trained and Domain Transferred Deep Networks
Sentiment analysis of online user generated content is important for many social media analytics tasks. Researchers have largely relied on textual sentiment analysis to develop sy...
Quanzeng You, Jiebo Luo, Hailin Jin, Jianchao Yang
AAAI
2015
8 years 8 months ago
Solving Games with Functional Regret Estimation
We propose a novel online learning method for minimizing regret in large extensive-form games. The approach learns a function approximator online to estimate the regret for choosi...
Kevin Waugh, Dustin Morrill, James Andrew Bagnell,...
AAAI
2015
8 years 8 months ago
Constructing Models of User and Task Characteristics from Eye Gaze Data for User-Adaptive Information Highlighting
A user-adaptive information visualization system capable of learning models of users and the visualization tasks they perform could provide interventions optimized for helping spe...
Matthew Gingerich, Cristina Conati
AAAI
2015
8 years 8 months ago
A Multivariate Timeseries Modeling Approach to Severity of Illness Assessment and Forecasting in ICU with Sparse, Heterogeneous
The ability to determine patient acuity (or severity of illness) has immediate practical use for clinicians. We evaluate the use of multivariate timeseries modeling with the multi...
Marzyeh Ghassemi, Marco A. F. Pimentel, Tristan Na...