Monotonic Simultaneous Translation with Chunk-wise Reordering and Refinement

Recent work in simultaneous machine translation is often trained with conventional full sentence translation corpora, leading to either excessive latency or necessity to anticipate as-yet-unarrived words, when dealing with a language pair whose word orders significantly differ. This is unlike human simultaneous interpreters who produce largely monotonic translations at the expense of the grammaticality of a sentence being translated. In this paper, we thus propose an algorithm to reorder and refine the target side of a full sentence translation corpus, so that the words/phrases between the source and target sentences are aligned largely monotonically, using word alignment and non-autoregressive neural machine translation. We then train a widely used wait-k simultaneous translation model on this reordered-and-refined corpus. The proposed approach improves BLEU scores and resulting translations exhibit enhanced monotonicity with source sentences.

Cross-Lingual Word Embedding Refinement by $\ell_1$ Norm Optimisation

Cross-Lingual Word Embeddings (CLWEs) encode words from two or more languages in a shared high-dimensional space in which vectors representing words with similar meaning (regardless of language) are closely located. Existing methods for building high-quality CLWEs learn mappings that minimise the ℓ2 norm loss function. However, this optimisation objective has been demonstrated to be sensitive to outliers. Based on the more robust Manhattan norm (aka. ℓ1 norm) goodness-of-fit criterion, this paper proposes a simple post-processing step to improve CLWEs. An advantage of this approach is that it is fully agnostic to the training process of the original CLWEs and can therefore be applied widely. Extensive experiments are performed involving ten diverse languages and embeddings trained on different corpora. Evaluation results based on bilingual lexicon induction and cross-lingual transfer for natural language inference tasks show that the ℓ1 refinement substantially outperforms four state-of-the-art baselines in both supervised and unsupervised settings. It is therefore recommended that this strategy be adopted as a standard for CLWE methods.

Numerical Simulation of 2D Numerical Wave Tank by the Resolution of Navier-Stokes Equations using Adaptive Selective Mesh Refinement Method

This paper deals with a numerical method based on the simulation of a 2D tank, for unsteady and laminar two - dimensional incompressible viscous flow. Navier-Stokes and Continuity equations are solved in a fluid domain. These equations are discretized by Finite Differences Method. The pressure is obtained by solving a Poisson equation dealing with a fictitious velocity field. The Poisson equation is solved by a Finite Volume Method. The grid is refined by a new method “Adaptive Selective Mesh Refinement” called “ASMR”.

Study the improvement of the thermal conductivity of The 6063 Aluminum Alloy by Alloy Elements Adding

In this research we are Studying the improvement of the thermal conductivity of The 6063 aluminum alloys by Alloy elements Adding such as (Boron & Titanium) . In this Study we used (6063) aluminum alloy as a base metal because it using of the fabrication of Central Processing Unit(CPU) heat sinks . First, we brought casting mold. We melted Aluminum after weighting it ,and we adding Alloy elements (Boron & Titanium), we selected the temperatures of the furnace at 1000 ℃ ,for period 60 minute.