Richard C. Wang

Coupled semi-supervised learning for information extraction

We consider the problem of semi-supervised learning to extract categories (e.g., academic fields, athletes) and relations (e.g., PlaysSport(athlete, sport)) from web pages, starting with a handful of labeled training examples of each category or relation, plus hundreds of millions of unlabeled web documents. Semi-supervised training using only a few labeled examples is typically unreliable because the learning task is underconstrained. This paper pursues the thesis that much greater accuracy can be achieved by further constraining the learning task, by coupling the semi-supervised training of many extractors for different categories and relations. We characterize several ways in which the training of category and relation extractors can be coupled, and present experimental results demonstrating significantly improved accuracy as a result.

Automatic Set Expansion for List Question Answering

This paper explores the use of set expansion (SE) to improve question answering (QA) when the expected answer is a list of entities belonging to a certain class. Given a small set of seeds, SE algorithms mine textual resources to produce an extended list including additional members of the class represented by the seeds. We explore the hypothesis that a noise-resistant SE algorithm can be used to extend candidate answers produced by a QA system and generate a new list of answers that is better than the original list produced by the QA system. We further introduce a hybrid approach which combines the original answers from the QA system with the output from the SE algorithm. Experimental results for several state-of-the-art QA systems show that the hybrid system performs better than the QA systems alone when tested on list question data from past TREC evaluations.

Improving Distant Supervision for Information Extraction Using Label Propagation Through Lists

Because of polysemy, distant labeling for information extraction leads to noisy training data. We describe a procedure for reducing this noise by using label propagation on a graph in which the nodes are entity mentions, and mentions are coupled when they occur in coordinate list structures. We show that this labeling approach leads to good performance even when off-the-shelf classifiers are used on the distantly-labeled data.

CMDragons 2015: Coordinated Offense and Defense of the SSL Champions

The CMDragons Small Size League SSL team won all of itsi¾ź6 games at RoboCup 2015, scoring a total of 48 goals and conceding 0. This paper presents the core coordination algorithms in offense and defense that enabled such successful performance. We first describe the coordinated plays layer that distributes the teams robots into offensive and defensive subteams. We then describe the offense and defense coordination algorithms to control these subteams. Effective coordination enables our robots to attain a remarkable level of team-oriented gameplay, persistent offense, and reliability during regular gameplay, shifting our strategy away from stopped ball plays. We support these statements and the effectiveness of our algorithms with statistics from our performance at RoboCup 2015.

Iterative Snapping of Odometry Trajectories for Path Identification

An increasing number of mobile devices are capable of automatically sensing and recording rich information about the surrounding environment. Spatial locations of such data can help to better learn about the environment. In this work, we address the problem of identifying the locations visited by a mobile device as it moves within an indoor environment. We focus on devices equipped with odometry sensors that capture changes in motion. Odometry suffers from cumulative errors of dead reckoning but it captures the relative shape of the traversed path well. Our approach will correct such errors by matching the shape of the trajectory from odometry to traversable paths of a known map. Our algorithm is inspired by prior vehicular GPS map matching techniques that snap global GPS measurements to known roads. We similarly wish to snap the trajectory from odometry to known hallways. Several modifications are required to ensure these techniques are robust when given relative measurements from odometry. If we assume an office-like environment with only straight hallways, then a significant rotation indicates a transition to another hallway. As a result, we partition the trajectory into line segments based on significant turns. Each trajectory segment is snapped to a corresponding hallway that best maintains the shape of the original trajectory. These snapping decisions are made based on the similarity of the two curves as well as the rotation to transition between hallways. We will show robustness under different types of noise in complex environments and the ability to propose coarse sensor noise errors.

Active sensing data collection with autonomous mobile robots

With the introduction of autonomous robots that help perform various tasks in our environments, we can opportunistically use them for collecting fine-grain sensor measurements about our surroundings. Use of mobile robots for data collection scales much better than static sensors in terms of number of measurement locations and provide more fine-grain accuracy and reliability than alternate human crowd-sourcing efforts. One of the unique features of mobile robots is the ability to control and direct where and when measurements should be collected. In this paper, we present a system to compute paths for the robot to follow that incorporates the robots limited expected deployment time, expected measurement value at each location, and a history of when each location was last visited.

Indoor trajectory identification: Snapping with uncertainty

We consider the problem of indoor human trajectory identification using odometry data from smartphone sensors. Given a segmented trajectory, a simplified map of the environment, and a set of error thresholds, we implement a map-matching algorithm in a urban setting and analyze the accuracy of the resulting path. We also discuss aggregation of user step data into a segmented trajectory. Besides providing an interesting application of learning human motion in a constrained environment, we examine how the uncertainty of the snapped trajectory varies with path length. We demonstrate that as new segments are added to a path, the number of possibilities for earlier segments is monotonically non-increasing. Applications of this work in an urban setting are discussed, as well as future plans to develop a formal theory of odometry-based map-matching.

O-Snap: Optimal snapping of odometry trajectories for route identification

An increasing number of wearable and mobile devices are capable of automatically sensing and recording rich information about the surrounding environment. To make use of such data, it is desirable for each data point to be matched with its corresponding spatial location. We focus on using the trajectory from a devices odometry sensors that reveal changes in motion over time. Our goal is to recover the route traversed, which we will define as a sequence of revisitable positions. Dead reckoning, which computes the devices route from its odometry trajectory, is known to suffer from significant drift over time. We aim to overcome drift errors by reshaping the odometry trajectory to fit the constraints of a given topological map and sensor noise model. Prior works use iterative search algorithms that are susceptible to local maximas [15], which means that they can be misled when faced with ambiguous decisions. In contrast, our algorithm is able to find the set of all routes within the given constraints. This also reveals if there are multiple routes that are similarly likely. We can then rank them and select the optimal route that is most likely to be the actual route. We also show that the algorithm can be extended to recover routes even in the presence of topological map errors. We evaluate our algorithm by recovering all routes traversed by a wheeled robot covering over 9 kilometers from its odometry sensor data.

Wireless map-based handoffs for mobile robots

Most wireless solutions today are centered around people-centric devices like laptops and cell phones that are insufficient for mobile robots. The key difference is that people-centric devices use wireless connectivity in bursts under primarily stationary settings while mobile robots continuously transmit data even while moving. When mobile robots use existing wireless solutions, it results in intolerable and seemingly random interruptions in wireless connectivity when moving [1]. These wireless issues stem from suboptimal switching across wireless infrastructure access points (APs), also called AP handoffs. These poor handoff decisions are due to stateless handoff algorithms that make wireless decisions solely from immediate and noisy scans of surrounding wireless conditions. In this paper, we propose to overcome these motion-based wireless connectivity issues for autonomous robots using highly informed handoff algorithms that combine fine-grain wireless maps with accurate robot localization. Our results show significant wireless performance improvements for continuously moving robots in real environments without any modifications to the wireless infrastructure.

Using Graphs of Classifiers to Impose Constraints on Semi-supervised Relation Extraction.

We propose a general approach to modeling semi-supervised learning constraints on unlabeled data. Both traditional supervised classification tasks and many natural semisupervised learning heuristics can be approximated by specifying the desired outcome of walks through a graph of classifiers. We demonstrate the modeling capability of this approach in the task of relation extraction, and experimental results show that the modeled constraints achieve better performance as expected.