No abstract

A finite element model has been established and used to predict the temperature history of direct laser fabricated (DLFed) Ti-6Al-4V thin wall samples. The effects of laser power and the effect of location within a sample on its temperature history have been modelled and compared with temperatures measured during DLF using thermocouples. The thermal history of the material has been correlated with the observed differences in the microstructures obtained at different locations in a given sample or for a given location in samples obtained at different laser powers.

Recent work on non-autoregressive neural machine translation (NAT) aims at improving the efficiency by parallel decoding without sacrificing the quality. However, existing NAT methods are either inferior to Transformer or require multiple decoding passes, leading to reduced speedup. We propose the Glancing Language Model (GLM) for single-pass parallel generation models. With GLM, we develop Glancing Transformer (GLAT) for machine translation. With only single-pass parallel decoding, GLAT is able to generate high-quality translation with 8×-15× speedup. Note that GLAT does not modify the network architecture, which is a training method to learn word interdependency. Experiments on multiple WMT language directions show that GLAT outperforms all previous single pass non-autoregressive methods, and is nearly comparable to Transformer, reducing the gap to 0.25-0.9 BLEU points.

Paraphrasing plays an important role in various natural language processing (NLP) tasks, such as question answering, information retrieval and sentence simplification. Recently, neural generative models have shown promising results in paraphrase generation. However, prior work mainly focused on single paraphrase generation, while ignoring the fact that diversity is essential for enhancing generalization capability and robustness of downstream applications. Few works have been done to solve diverse paraphrase generation. In this paper, we propose a novel approach with two discriminators and multiple generators to generate a variety of different paraphrases. A reinforcement learning algorithm is applied to train our model. Our experiments on two realworld datasets demonstrate that our model not only gains a significant increase in diversity but also improves generation quality over several state-of-the-art baselines.

No abstract