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)
Recent studies have suggested glaucomatous loss of retinal ganglion cells and their axons in Alzheimer's disease. Amyloid beta peptides and phosphorylated tau protein have been implicated in the selective regional neuronal loss and protein accumulations characteristic of Alzheimer's disease. Similar protein accumulations are not present on glaucomatous(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)
Reversible acetylation of α-tubulin is an evolutionarily conserved modification in microtubule networks. Despite its prevalence, the physiological function and regulation of microtubule acetylation remain poorly understood. Here we report that macrophages challenged by bacterial lipopolysaccharides (LPS) undergo extensive microtubule acetylation.(More)
In this study, we evaluated the role of tumor cell and tumor stroma sensitivity as determinants of radiation-induced tumor growth delay. A DNA double-strand break repair–defective DNA-PKcs À/À tumor cell line and its radioresistant DNA-PKcs +/+ –transfected counterpart were used to initiate tumors in nude and hypersensitive severe combined immunodeficient(More)