Learn More
We present a system that learns to follow navigational natural language directions. Where traditional models learn from linguistic annotation or word distributions, our approach is grounded in the world, learning by apprenticeship from routes through a map paired with English descriptions. Lacking an explicit alignment between the text and the reference(More)
Conversational implicatures involve reasoning about multiply nested belief structures. This complexity poses significant challenges for computational models of conversation and cognition. We show that agents in the multi-agent DecentralizedPOMDP reach implicature-rich interpretations simply as a by-product of the way they reason about each other to maximize(More)
Online marketplaces increasingly act as intermediaries in labor, housing, dating, and other markets where traders match with each other. These marketplaces use novel data generated by users’ activities on the website to design algorithms and products that influence the search and matching process. I use internal data from Airbnb, a prominent online(More)
Deciding what mix of engine and battery power to use is critical to hybrid vehicles’ fuel efficiency. Current solutions consider several factors such as the charge of the battery and how efficient the engine operates at a given speed. Previous research has shown that by taking into account the future power requirements of the vehicle, a more efficient(More)
Grice characterized communication in terms of the cooperative principle, which enjoins speakers to make only contributions that serve the evolving conversational goals. We show that the cooperative principle and the associated maxims of relevance, quality, and quantity emerge from multi-agent decision theory. We utilize the Decentralized Partially(More)
We present a novel simple technique for stimulating distal esophageal pouch growth in a patient with isolated, long-gap esophageal atresia. In this case report, distal esophageal growth was achieved through daily intermittent pressurization via a surgically placed indwelling balloon catheter. The patient ultimately underwent successful, uncomplicated,(More)
Recursive Bayesian models of linguistic communication capture a variety of intricate kinds of pragmatic enrichment, but they tend to depend on the unrealistic assumption that agents are invariably optimal reasoners. We present a discriminative model that seeks to capitalize on the insights of such approaches while addressing these concerns about inferential(More)
Despite efforts to build robust vision systems, robots in new environments inevitably encounter new objects. Traditional supervised learning requires gathering and annotating sample images in the environment, usually in the form of bounding boxes or segmentations. This training interface takes some experience to do correctly and is quite tedious. We report(More)
BACKGROUND Vascular anomalies are vascular tumors and congenital malformations that rarely involve the pancreas. Diagnosis and management of these lesions is complex. METHODS An institutional review board-approved retrospective database and record review from 1994 through 2004 at a quaternary referral center for vascular anomalies was conducted. RESULTS(More)
The role of minimally invasive surgery (MIS) in children with solid neoplasms is slowly evolving. MIS appears to be an ideal way to obtain diagnostic information (i.e., tissue biopsy) in children with solid neoplasms, but its role as an ablative/curative technique is controversial. We examined the safety, reliability, and outcome of decisions made on the(More)