Learn More
We present a novel commentator system that learns language from sportscasts of simulated soccer games. The system learns to parse and generate commentaries without any engineered knowledge about the English language. Training is done using only ambiguous supervision in the form of textual human commentaries and simulation states of the soccer games. The(More)
The ability to understand natural-language instructions is critical to building intelligent agents that interact with humans. We present a system that learns to transform natural-language navigation instructions into executable formal plans. Given no prior linguistic knowledge, the system learns by simply observing how humans follow navigation instructions.(More)
We present a novel framework for learning to interpret and generate language using only perceptual context as supervision. We demonstrate its capabilities by developing a system that learns to sportscast simulated robot soccer games in both English and Korean without any language-specific prior knowledge. Training employs only ambiguous supervision(More)
An error occurs when software cannot complete a requested action as a result of some problem with its input, configuration, or environment. A high-quality error report allows a user to understand and correct the problem. Unfortunately, the quality of error reports has been decreasing as software becomes more complex and layered. End-users take the cryptic(More)
Traditional methods of collecting translation and paraphrase data are prohibitively expensive, making the construction of large, new corpora difficult. While crowdsourcing offers a cheap alternative, quality control and scalability can become problematic. We discuss a novel annotation task that uses videos as the stimulus which discourages cheating. In(More)
One of the key challenges in grounded language acquisition is resolving the intentions of the expressions. Typically the task involves identifying a subset of records from a list of candidates as the correct meaning of a sentence. While most current work assume complete or partial independence between the records, we examine a scenario in which they are(More)
This is a partial list of publications that have resulted, directly or indirectly, from the RoboCup Simluation leagues. It was compiled by requesting contributions from subscribers to the simulation league mailing lists, last in July 2013. There are certainly many other publications that have not been included in this list. If you know of any, please send(More)
This paper presents a novel pulse oximeter design for monitoring physiologic parameters and demonstrates the feasibility of extracting accurate heart rate (HR)and blood oxygen saturation (SpO2)from a reflection type photo plethysmographic (PPG)sensor. The time domain processing algorithm is used to enhance the accuracy in real-time detection. This study may(More)
The ability to understand natural-language instructions is critical to building intelligent agents that interact with humans. We present a system that learns to transform natural-language navigation instructions into executable formal plans. Given no prior linguistic knowledge, the system learns by simply observing how humans follow navigation instructions.(More)
  • 1