With the rapid urbanization, many cities have faced the problem about the reducing areas of public spaces. Many of the public spaces which are available to urban residents is compressed due to unreasonable urban planning. Among the 17 sustainable development goals proposed by the United Nations in 2015, the goal 11 is sustainable cities and human settlements, in which, the indicator 11.7.1 is the urban public space that residents can accessible. This paper used GF-2 satellite imagery to extract the information of urban features such as buildings, roads, and green spaces in Xi'an, China by means of deep learning technology. Combined with the urban population statistics, the per capita public space, green space rate and other information in Xi'an were calculated based on the SDG11.7.1 index calculation model, Compared with the 11.7.1 indicators results from the UN report, it shows that the per capita activity public space in Xi'an is at a medium level, while there is a problem of uneven distribution of urban public space. Based on the research results of GF-2 images, this paper can provide decision support for the urban planning of public space in Xi'an.

Wanying Xie, Yang Feng, Shuhao Gu, Dong Yu. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Domain Adaptation is widely used in practical applications of neural machine translation, which aims to achieve good performance on both general domain and in-domain data.However, the existing methods for domain adaptation usually suffer from catastrophic forgetting, large domain divergence, and model explosion.To address these three problems, we propose a method of "divide and conquer" which is based on the importance of neurons or parameters for the translation model.In this method, we first prune the model and only keep the important neurons or parameters, making them responsible for both generaldomain and in-domain translation.Then we further train the pruned model supervised by the original whole model with knowledge distillation.Last we expand the model to the original size and fine-tune the added parameters for the in-domain translation.We conducted experiments on different language pairs and domains and the results show that our method can achieve significant improvements compared with several strong baselines.

Neural machine translation models usually adopt the teacher forcing strategy for training which requires the predicted sequence matches ground truth word by word and forces the probability of each prediction to approach a 0-1 distribution. However, the strategy casts all the portion of the distribution to the ground truth word and ignores other words in the target vocabulary even when the ground truth word cannot dominate the distribution. To address the problem of teacher forcing, we propose a method to introduce an evaluation module to guide the distribution of the prediction. The evaluation module accesses each prediction from the perspectives of fluency and faithfulness to encourage the model to generate the word which has a fluent connection with its past and future translation and meanwhile tends to form a translation equivalent in meaning to the source. The experiments on multiple translation tasks show that our method can achieve significant improvements over strong baselines.

There exists a token imbalance phenomenon in natural language as different tokens appear with different frequencies, which leads to different learning difficulties for tokens in Neural Machine Translation (NMT).The vanilla NMT model usually adopts trivial equal-weighted objectives for target tokens with different frequencies and tends to generate more high-frequency tokens and less lowfrequency tokens compared with the golden token distribution.However, low-frequency tokens may carry critical semantic information that will affect the translation quality once they are neglected.In this paper, we explored target token-level adaptive objectives based on token frequencies to assign appropriate weights for each target token during training.We aimed that those meaningful but relatively low-frequency words could be assigned with larger weights in objectives to encourage the model to pay more attention to these tokens.Our method yields consistent improvements in translation quality on ZH-EN, EN-RO, and EN-DE translation tasks, especially on sentences that contain more low-frequency tokens where we can get 1.68, 1.02, and 0.52 BLEU increases compared with baseline, respectively.Further analyses show that our method can also improve the lexical diversity of translation.