The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Discriminative language modeling is a structured classification problem. Log-linear models have been previously used to address this problem. In this paper, the standard dot-product feature representation used in log-linear models is replaced by a non-linear function parameterized by a neural network. Embeddings are learned for each word and features are extracted automatically through the use of...
We present our work on semi-supervised learning of discriminative language models where the negative examples for sentences in a text corpus are generated using confusion models for Turkish at various granularities, specifically, word, sub-word, syllable and phone levels. We experiment with different language models and various sampling strategies to select competing hypotheses for training with a...
This paper investigates semi-supervised methods for discriminative language modeling, whereby n-best lists are “hallucinated” for given reference text and are then used for training n-gram language models using the perceptron algorithm. We perform controlled experiments on a very strong baseline English CTS system, comparing three methods for simulating ASR output, and compare the results with training...
We describe the effect of the equivalent pre-crack size (EPS) distribution errors on probability of failure (PF) of an FA/18 bulkhead. We distinguish two types of errors: (1) measurement errors of the EPS distribution parameters and (2) errors that arise because PF is typically calculated based on an EPS distribution with an infinite tail, while in a flying aircraft the tail cannot be unbounded. Our...
Evaluating risk of aircraft failure is necessary for scheduling appropriate maintenance, avoiding aircraft losses and mission failures, maintaining a high level of readiness, and estimating aircraft fleet aging. This paper presents the results of calculating aircraft failure risk by estimating the probability of structural failure of F-18 wing attachment bulkheads. Laboratory fatigue-crack growth-test...
Achieving high reliability of military platforms is critical for reducing operating costs and increasing operational availability and combat readiness. This paper describes results of a comparative analysis of two approaches to improving platform reliability. The first is based on platform inspections (performed at specific time intervals) and replacement of parts whose remaining life is found to...
Achieving high reliability is one of the major objectives in the development of the future combat system (FCS) family of military vehicles. The proposed solution to achieve this objective is a prognostics-based approach characterized by a capability to monitor the status of mission-critical components and forecast the future state of the FCS system. In this paper, two approaches for achieving and...
Since the rapid flybys of Mariner 10 in the late seventies, Mercury is known to have an intrinsic magnetic field that dominates the interactions of Mercury with its space environment. Even though important aspects of this interaction have been probed by the Mariner 10 instruments, crucial aspects remain unknown and unexplored. In particular there are fundamental uncertainties concerning the ion content...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.