This paper addresses the problem of automatically selecting the best among outputs from multiple machine translation (MT) systems. Existing approaches select the output assigned the highest score according to a target language model. In some cases, the existing approaches do not work well. This paper proposes two methods to improve performance. The rst method is based on a m ultiple comparison test and checks whether a score from language and translation models is signicantly higher than the others. The second method is based on probability that a translation is not inferior to the others, which is predicted from the above scores. Experimental results show that the proposed methods achieve an improvement o f 2 t o 6 % in performance.
ABSTRACT. To prevent encephalomyelitis caused by Akabane virus, as observed in 2006, vaccination of calves is one of the most effective prophylactic measures. For vaccination of calves, the duration of the maternal antibodies need to be considered because these antibodies are an obstacle to the effectiveness of the vaccine. In order to estimate the age of antibody decay in calves and to find factors influencing the duration of passive immunity, we conducted survival analysis using data from nationwide sentinel surveillance for Akabane disease. The accelerated failure time model based on the presence of interval censored data was used. The best fit model with a log-logistic distribution indicated that the maternal antibodies of beef calves last 1.11 times longer (95% confidence interval [CI]=1.06-1.16) than those of dairy calves. Calves in the western part of Japan and on Kyushu island, Japan, maintained the maternal antibodies 1.17 times (95% CI=1.11-1.23 and 1.10-1.24, respectively) longer than those in the eastern part of Japan. The ages at which beef calves in the eastern part of Japan, western part of Japan and Kyushu loose the antibodies, with 90% probability, were estimated to be 4.1, 4.8 and 4.8 months, respectively, while the ages were 3.7, 4.3 and 4.3 months for dairy calves in the same regions. The duration of maternal immunity to Akabane virus was different for different types of cattle and among different regions. These differences need to be taken into account when a vaccination strategy is adopted for preventing epizootic encephalomyelitis in the future.KEY WORDS: AFT model, akabane virus, maternal antibody, survival analysis.
This paper addresses the challenging problem of automatically evaluating output from machine translation (MT) systems in order to support the developers of these systems. Conventional approaches to the problem include methods that automatically assign a rank such as A, B, C, or D to MT output according to a single edit distance between this output and a correct translation example. The single edit distance can be differently designed, but changing its design makes assigning a certain rank more accurate, but another rank less accurate. This inhibits improving accuracy of rank assignment. To overcome this obstacle, this paper proposes an automatic ranking method that, by using multiple edit distances, encodes machine-translated sentences with a rank assigned by humans into multi-dimensional vectors from which a classifier of ranks is learned in the form of a decision tree (DT). The proposed method assigns a rank to MT output through the learned DT. The proposed method is evaluated using transcribed texts of real conversations in the travel arrangement domain. Experimental results show that the proposed method is more accurate than the single-edit-distance-based ranking methods, in both closed and open tests. Moreover, the proposed method could estimate MT quality within 3% error in some cases.
This paper reports the latest performance of components and features of a project named Corpus-Centered Computation (C'3), which targets a translation technology suitable for spoken language translation. C3 places corpora at the center of the technology. Translation knowledge is extracted from corpora by both EBMT and SMT methods, translation quality is gauged by referring to corpora, the best translation among multiple-engine outputs is selected based on corpora and the corpora themselves are paraphrased or filtered by automated processes.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.