In standard training regimes, one assumes that the classes presented to a model constitute all of the classes that the model will encounter when it is deployed. In real deployment scenarios, however, a model can sometimes encounter situations or objects that it has never seen. When these scenarios are safety-critical,...
Sequential supervised learning problems involve assigning a class label to each item in a sequence. Examples include part-of-speech tagging and text-to-speech mapping. A very general-purpose strategy for solving such problems is to construct a recurrent sliding window (RSW) classifier, which maps some window of the input sequence plus some number...
Previous work introduced the GenderMag method, a software inspection method used to help software creators identify features within their software that are not gender-inclusive. Inclusiveness of software (gender or otherwise) matters because supporting diversity matters—it is well-known that the more diverse a group of problem-solvers, the higher the quality of...
Newcomers’ seamless onboarding is important for open collaboration communi- ties, particularly those that leverage outsiders’ contributions to remain sustainable. Nevertheless, previous work shows that OSS newcomers often face several barriers to contribute, which lead them to lose motivation and even give up on contributing. A well-known way to help newcomers...
Autonomous robotic agents are on their way to becoming in-home personal assistants, construction assistants, and warehouse workers. The degree of autonomy of such systems is reflected by the manner in which we specify goals to them; the abstraction of low-level commands to high-level goals goes hand-in-hand with increased autonomy. In...
This thesis presents a case study of applying machine learning tools to build a predictive
model of annual infestations of grasshoppers in Eastern Oregon. The purpose of the
study was two-fold. First, we wanted to develop a predictive model. Second, we wanted
to explore the capabilities of existing machine learning...
Most tasks in natural language processing (NLP) try to map structured input (e.g., sentence or word sequence) to some form of structured output (tag sequence, parse tree, semantic graph, translated/paraphrased/compressed sentence), a problem known as “structured prediction”. While various learning algorithms such as the perceptron, maximum entropy, and expectation-maximization have...
Information about named entities (real-world objects) is usually harvested from different sources and organized as a multiple relational directed graph in Knowledge Bases (KBs). KBs play essential roles in many NLP modules including question answering, fact-checking, search engines, etc. KBs are big but still incomplete: relational information among entities is...
This paper addresses the high model complexity and overconfident frame labeling of state-of-the-art (SOTA) action segmenters. Their complexity is typically justified by the need to sequentially refine action segmentation through multiple stages of a deep architecture. However, this multistage refinement does not take into account uncertainty of frame labeling predicted...