An Investigation of the Sampling-Based Alignment Method and Its Contributions
By investigating the distribution of phrase pairs in phrase translation tables, the work in this paper describes an approach to increase the number of n-gram alignments in phrase translation tables output by a sampling-based alignment method. This approach consists in enforcing the alignment of n-grams in distinct translation subtables so as to increase the number of n-grams. Standard normal distribution is used to allot alignment time among translation subtables, which results in adjustment of the distribution of n- grams. This leads to better evaluation results on statistical machine translation tasks than the original sampling-based alignment approach. Furthermore, the translation quality obtained by merging phrase translation tables computed from the sampling-based alignment method and from MGIZA++ is examined.
Code (0)
등록된 구현이 없습니다.
Tasks
Machine TranslationTranslationSimilar Papers 제목 키워드 기반
Negative Sampling in Knowledge Graph Representation Learning: A Review
Knowledge Graph Representation Learning (KGRL), or Knowledge Graph Embedding (KGE), is essential for AI applications such as knowledge construction and information retrieval. These models encode entities and relations in…
Graph EmbeddingGraph Representation LearningInformation RetrievalKnowledge Graph Embedding+5A Taxonomy of Conceptual Alignment in Human-Robot Dialogue
Successful conversations require speakers to align on the meaning of concepts, a challenging but crucial task for human-robot interaction. Understanding the process of establishing such alignment is hindered by competing…
Data-Efficient Training by Evolved Sampling
Data selection is designed to accelerate learning with preserved performance. To achieve this, a fundamental thought is to identify informative data samples with significant contributions to the training. In this work, w…
Direct loss minimization algorithms for sparse Gaussian processes
The paper provides a thorough investigation of Direct loss minimization (DLM), which optimizes the posterior to minimize predictive loss, in sparse Gaussian processes. For the conjugate case, we consider DLM for log-loss…
Computational EfficiencyGaussian ProcessesHyperparameter OptimizationStochastic Optimization+1Investigation of D-Wave quantum annealing for training Restricted Boltzmann Machines and mitigating catastrophic forgetting
Modest statistical differences between the sampling performances of the D-Wave quantum annealer (QA) and the classical Markov Chain Monte Carlo (MCMC), when applied to Restricted Boltzmann Machines (RBMs), are explored t…
Incremental Learning