Learning Translation Consensus with Structured Label Propagation
نویسندگان
چکیده
In this paper, we address the issue for learning better translation consensus in machine translation (MT) research, and explore the search of translation consensus from similar, rather than the same, source sentences or their spans. Unlike previous work on this topic, we formulate the problem as structured labeling over a much smaller graph, and we propose a novel structured label propagation for the task. We convert such graph-based translation consensus from similar source strings into useful features both for n-best output reranking and for decoding algorithm. Experimental results show that, our method can significantly improve machine translation performance on both IWSLT and NIST data, compared with a state-ofthe-art baseline.
منابع مشابه
Large Scale Translation Quality Estimation
This study explores methods for developing a large scale Quality Estimation framework for Machine Translation. We expand existing resources for Quality Estimation across related languages by using different transfer learning methods. The transfer learning methods are: Transductive SVM, Label Propagation and Self-taught Learning. We use transfer learning methods on the available labelled dataset...
متن کاملPropagation Kernels for Partially Labeled Graphs
Learning from complex data is becoming increasingly important, and graph kernels have recently evolved into a rapidly developing branch of learning on structured data. However, previously proposed kernels rely on having discrete node label information. Propagation kernels leverage the power of continuous node label distributions as graph features and hence, enhance traditional graph kernels to ...
متن کاملE cient Graph Kernels by Randomization
Learning from complex data is becoming increasingly important, and graph kernels have recently evolved into a rapidly developing branch of learning on structured data. However, previously proposed kernels rely on having discrete node label information. In this paper, we explore the power of continuous node-level features for propagation-based graph kernels. Speci cally, propagation kernels expl...
متن کاملMulti-Label Zero-Shot Learning with Structured Knowledge Graphs
In this paper, we propose a novel deep learning architecture for multi-label zero-shot learning (ML-ZSL), which is able to predict multiple unseen class labels for each input instance. Inspired by the way humans utilize semantic knowledge between objects of interests, we propose a framework that incorporates knowledge graphs for describing the relationships between multiple labels. Our model le...
متن کاملTeaching-to-Learn and Learning-to-Teach for Multi-label Propagation
Multi-label propagation aims to transmit the multi-label information from labeled examples to unlabeled examples based on a weighted graph. Existing methods ignore the specific propagation difficulty of different unlabeled examples and conduct the propagation in an imperfect sequence, leading to the error-prone classification of some difficult examples with uncertain labels. To address this pro...
متن کامل