0%

【arxiv论文】 Computation and Language 2020-02-03

发表于 2020-02-03 更新于 2020-03-05 分类于 arxiv ， CL 16k 26 分钟

目录

1. Pretrained Transformers for Simple Question Answering over Knowledge Graphs [PDF] 摘要

2. An efficient automated data analytics approach to large scale computational comparative linguistics [PDF] 摘要

3. Hybrid Tiled Convolutional Neural Networks for Text Sentiment Classification [PDF] 摘要

4. Break It Down: A Question Understanding Benchmark [PDF] 摘要

5. Teaching Machines to Converse [PDF] 摘要

6. Pseudo-Bidirectional Decoding for Local Sequence Transduction [PDF] 摘要

7. Self-Adversarial Learning with Comparative Discrimination for Text Generation [PDF] 摘要

8. Augmenting Visual Question Answering with Semantic Frame Information in a Multitask Learning Approach [PDF] 摘要

9. Enhancement of Short Text Clustering by Iterative Classification [PDF] 摘要

10. Unwanted Advances in Higher Education: Uncovering Sexual Harassment Experiences in Academia with Text Mining [PDF] 摘要

阅读全文 »

pip 安装提示空间不足

发表于 2020-01-21 分类于技术杂谈 160 1 分钟

pip

pip 安装提示空间不足

1	Could not install packages due to an EnvironmentError: [Errno 28] No space left on device

这是服务器上的/tmp空间不足，可以在自己的根目录下简历~/tmp代替 /tmp

1 2	mkdir ~/tmp export TMPDIR=$HOME/tmp

【arxiv论文】 Computer Vision and Pattern Recognition 2020-01-20

发表于 2020-01-20 更新于 2020-03-05 分类于 arxiv ， CV 57k 1:34

目录

1. Unsupervised Learning of Camera Pose with Compositional Re-estimation [PDF] 摘要

2. Combining PRNU and noiseprint for robust and efficient device source identification [PDF] 摘要

3. TailorGAN: Making User-Defined Fashion Designs [PDF] 摘要

4. Subjective Annotation for a Frame Interpolation Benchmark using Artifact Amplification [PDF] 摘要

5. GraphBGS: Background Subtraction via Recovery of Graph Signals [PDF] 摘要

6. Latency-Aware Differentiable Neural Architecture Search [PDF] 摘要

7. BigEarthNet Deep Learning Models with A New Class-Nomenclature for Remote Sensing Image Understanding [PDF] 摘要

8. Efficient Facial Feature Learning with Wide Ensemble-based Convolutional Neural Networks [PDF] 摘要

9. Vision Meets Drones: Past, Present and Future [PDF] 摘要

10. Predicting the Physical Dynamics of Unseen 3D Objects [PDF] 摘要

11. Review: deep learning on 3D point clouds [PDF] 摘要

12. Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network [PDF] 摘要

13. SieveNet: A Unified Framework for Robust Image-Based Virtual Try-On [PDF] 摘要

14. Two-Phase Object-Based Deep Learning for Multi-temporal SAR Image Change Detection [PDF] 摘要

15. Registration made easy -- standalone orthopedic navigation with HoloLens [PDF] 摘要

16. FPCR-Net: Feature Pyramidal Correlation and Residual Reconstruction for Semi-supervised Optical Flow Estimation [PDF] 摘要

17. Interpreting Galaxy Deblender GAN from the Discriminator's Perspective [PDF] 摘要

18. Learning to Augment Expressions for Few-shot Fine-grained Facial Expression Recognition [PDF] 摘要

19. Spatio-Temporal Ranked-Attention Networks for Video Captioning [PDF] 摘要

20. Automatic Discovery of Political Meme Genres with Diverse Appearances [PDF] 摘要

21. On- Device Information Extraction from Screenshots in form of tags [PDF] 摘要

22. Tracking of Micro Unmanned Aerial Vehicles: A Comparative Study [PDF] 摘要

23. Increasing the robustness of DNNs against image corruptions by playing the Game of Noise [PDF] 摘要

24. Modality-Balanced Models for Visual Dialogue [PDF] 摘要

25. Tethered Aerial Visual Assistance [PDF] 摘要

26. DeepSUM++: Non-local Deep Neural Network for Super-Resolution of Unregistered Multitemporal Images [PDF] 摘要

27. Detection Method Based on Automatic Visual Shape Clustering for Pin-Missing Defect in Transmission Lines [PDF] 摘要

28. Sideways: Depth-Parallel Training of Video Models [PDF] 摘要

29. FedVision: An Online Visual Object Detection Platform Powered by Federated Learning [PDF] 摘要

30. Spatiotemporal Camera-LiDAR Calibration: A Targetless and Structureless Approach [PDF] 摘要

31. An adversarial learning framework for preserving users' anonymity in face-based emotion recognition [PDF] 摘要

32. Code-Bridged Classifier (CBC): A Low or Negative Overhead Defense for Making a CNN Classifier Robust Against Adversarial Attacks [PDF] 摘要

33. Curriculum Labeling: Self-paced Pseudo-Labeling for Semi-Supervised Learning [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-01-20

发表于 2020-01-20 更新于 2020-03-05 分类于 arxiv ， CL 14k 24 分钟

目录

1. A Common Semantic Space for Monolingual and Cross-Lingual Meta-Embeddings [PDF] 摘要

2. Modality-Balanced Models for Visual Dialogue [PDF] 摘要

3. A Hybrid Solution to Learn Turn-Taking in Multi-Party Service-based Chat Groups [PDF] 摘要

4. RobBERT: a Dutch RoBERTa-based Language Model [PDF] 摘要

5. Multi-step Joint-Modality Attention Network for Scene-Aware Dialogue System [PDF] 摘要

6. Plato Dialogue System: A Flexible Conversational AI Research Platform [PDF] 摘要

7. Supervised Speaker Embedding De-Mixing in Two-Speaker Environment [PDF] 摘要

8. On- Device Information Extraction from Screenshots in form of tags [PDF] 摘要

9. User-in-the-loop Adaptive Intent Detection for Instructable Digital Assistant [PDF] 摘要

阅读全文 »

python gtts 文本转语音

发表于 2020-01-19 分类于技术杂谈 156 1 分钟

tts

安装gtts

1	pip install gTTS

文本转语音

1
2
3

from gtts import gTTS
tts = gTTS(text="Hello World", lang='en')
tts.save("helloworld.mp3")

播放语音

1 2	import os os.system("start helloworld.mp3")

python 调用谷歌翻译接口

发表于 2020-01-19 更新于 2020-02-27 分类于技术杂谈 2.3k 4 分钟

python 谷歌翻译

googletrans 是一个封装了谷歌翻译接口的python代码库，可以通过googletrans实现免费、无限制调用谷歌翻译接口。

安装

1	pip install googletrans

翻译

from googletrans import Translator
translator = Translator(service_urls=[
      'translate.google.cn',])# 如果可以上外网，还可添加 'translate.google.com' 等
trans=translator.translate('Hello World', src='en', dest='zh-cn')
# 原文
print(trans.origin)
# 译文
print(trans.text)

阅读全文 »

【arxiv论文】 Computation and Language 2020-01-17

发表于 2020-01-18 更新于 2020-03-05 分类于 arxiv ， CL 25k 41 分钟

目录

1. Lexical Sememe Prediction using Dictionary Definitions by Capturing Local Semantic Correspondence [PDF] 摘要

2. Speech Emotion Recognition Based on Multi-feature and Multi-lingual Fusion [PDF] 摘要

3. Comparing Rule-based, Feature-based and Deep Neural Methods for De-identification of Dutch Medical Records [PDF] 摘要

4. A Pilot Study on Multiple Choice Machine Reading Comprehension for Vietnamese Texts [PDF] 摘要

5. AandP: Utilizing Prolog for converting between active sentence and passive sentence with three-steps conversion [PDF] 摘要

6. Schema2QA: Answering Complex Queries on the Structured Web with a Neural Model [PDF] 摘要

7. Stereotypical Bias Removal for Hate Speech Detection Task using Knowledge-based Generalizations [PDF] 摘要

8. AggressionNet: Generalised Multi-Modal Deep Temporal and Sequential Learning for Aggression Identification [PDF] 摘要

9. #MeToo on Campus: Studying College Sexual Assault at Scale Using Data Reported on Social Media [PDF] 摘要

10. Show, Recall, and Tell: Image Captioning with Recall Mechanism [PDF] 摘要

11. "Why is 'Chicago' deceptive?" Towards Building Model-Driven Tutorials for Humans [PDF] 摘要

12. Ensemble based discriminative models for Visual Dialog Challenge 2018 [PDF] 摘要

13. Discoverability in Satellite Imagery: A Good Sentence is Worth a Thousand Pictures [PDF] 摘要

14. Document Network Projection in Pretrained Word Embedding Space [PDF] 摘要

15. Delving Deeper into the Decoder for Video Captioning [PDF] 摘要

16. Insertion-Deletion Transformer [PDF] 摘要

阅读全文 »

一些公司及高校在线翻译系统

发表于 2020-01-17 47 1 分钟

公司在线翻译系统

高校在线翻译系统

厦门大学