深度学习在软件工程研究中应用的系统综述、结合知识图谱的图神经网络句子关系抽取方法(REECON)、用神经网络机器翻译框架​提取死亡因果链、超轻量OCR文字识别系统PP-OCR、从姿态序列感知情绪的零样本学习架构(SC-AAE)

 

LG - 机器学习   CV - 计算机视觉   CL - 计算与语言1、[LG] A Systematic Literature Review on the Use of Deep Learning in Software Engineering Research

C Watson, N Cooper, D N Palacio, K Moran, D Poshyvanyk [Washington & Lee University & William & Mary & George Mason University] 

深度学习在软件工程研究中应用的系统综述，针对软件工程和深度学习的交叉研究领域，给出了一个系统的文献综述，覆盖84篇论文，22个独特的软件工程任务，围绕学习的组成部分进行分析，在细粒度级别讨论了交叉研究的各个方面，最终得到一个研究路线图，描绘了应用于软件工程研究的深度学习技术，以及未来可能的更广泛的探索领域。

An increasingly popular set of techniques adopted by software engineering (SE) researchers to automate development tasks are those rooted in the concept of Deep Learning (DL). The popularity of such techniques largely stems from their automated feature engineering capabilities, which aid in modeling software artifacts. However, due to the rapid pace at which DL techniques have been adopted, it is difficult to distill the current successes, failures, and opportunities of the current research landscape. In an effort to bring clarity to this cross-cutting area of work, from its modern inception to the present, this paper presents a systematic literature review of research at the intersection of SE & DL. The review canvases work appearing in the most prominent SE and DL conferences and journals and spans 84 papers across 22 unique SE tasks. We center our analysis around the components of learning, a set of principles that govern the application of machine learning techniques (ML) to a given problem domain, discussing several aspects of the surveyed work at a granular level. The end result of our analysis is a research roadmap that both delineates the foundations of DL techniques applied to SE research, and likely areas of fertile exploration for the future.

https://weibo.com/1402400261/JmEGUAcJR

2、[CL] RECON: Relation Extraction using Knowledge Graph Context in a Graph Neural NetworkA Bastos, A Nadgeri, K Singh, I O Mulang, S Shekarpour, J Hoffart 

[Indian Institute of Technology & RWTH Aachen and Zerotha Research & Cerence GmbH and Zerotha Research & Fraunhofer IAIS and Zerotha & University of Dayton & Goldman Sachs]

结合知识图谱的图神经网络句子关系抽取方法(RECON)，用图神经网络同时学习句子表示和知识图谱中的事实——包括实体属性(标签、别名、描述、实例)和事实三元组，以提高整体抽取质量In this paper, we present a novel method named RECON, that automatically identifies relations in a sentence (sentential relation extraction) and aligns to a knowledge graph (KG). RECON uses a graph neural network to learn representations of both the sentence as well as facts stored in a KG, improving the overall extraction quality. These facts, including entity attributes (label, alias, description, instance-of) and factual triples, have not been collectively used in the state of the art methods. We evaluate the effect of various forms of representing the KG context on the performance of RECON. The empirical evaluation on two standard relation extraction datasets shows that RECON significantly outperforms all state of the art methods on NYT Freebase and Wikidata datasets. RECON reports 87.23 F1 score (Vs 82.29 baseline) on Wikidata dataset whereas on NYT Freebase, reported values are 87.5(P@10) and 74.1(P@30) compared to the previous baseline scores of 81.3(P@10) and 63.1(P@30).。

https://weibo.com/1402400261/JmEOBuvTh

3、[LG] Public Health Informatics: Proposing Causal Sequence of Death Using Neural Machine Translation

Y Zhu, Y Sha, H Wu, M Li, R A. Hoffman, M D. Wang [Georgia Institute of Technology & University of Science and Technology of China] 

用神经网络机器翻译框架提取死亡因果链，支持及时、准确和完整的死亡报告，基于死者的最后住院出院记录，确定导致死亡的临床条件的长时序列针对死亡因果链提取的三个主要挑战——两种版本的临床编码系统、医学领域知识冲突和数据互操作性，用神经网络机器翻译模型生成目标序列。

Each year there are nearly 57 million deaths around the world, with over 2.7 million in the United States. Timely, accurate and complete death reporting is critical in public health, as institutions and government agencies rely on death reports to analyze vital statistics and to formulate responses to communicable diseases. Inaccurate death reporting may result in potential misdirection of public health policies. Determining the causes of death is, nevertheless, challenging even for experienced physicians. To facilitate physicians in accurately reporting causes of death, we present an advanced AI approach to determine a chronically ordered sequence of clinical conditions that lead to death, based on decedents last hospital admission discharge record. The sequence of clinical codes on the death report is named as causal chain of death, coded in the tenth revision of International Statistical Classification of Diseases (ICD-10); the priority-ordered clinical conditions on the discharge record are coded in ICD-9. We identify three challenges in proposing the causal chain of death: two versions of coding system in clinical codes, medical domain knowledge conflict, and data interoperability. To overcome the first challenge in this sequence-to-sequence problem, we apply neural machine translation models to generate target sequence. We evaluate the quality of generated sequences with the BLEU (BiLingual Evaluation Understudy) score and achieve 16.44 out of 100. To address the second challenge, we incorporate expert-verified medical domain knowledge as constraint in generating output sequence to exclude infeasible causal chains. Lastly, we demonstrate the usability of our work in a Fast Healthcare Interoperability Resources (FHIR) interface to address the third challenge.

https://weibo.com/1402400261/JmEUgxayC

4、[CV] PP-OCR: A Practical Ultra Lightweight OCR SystemY Du, C Li, R Guo, X Yin, W Liu, J Zhou, Y Bai, Z Yu, Y Yang, Q Dang, H Wang 

[Baidu Inc] 超轻量OCR文字识别系统PP-OCR，引入一系列策略来增强模型能力或简化模型，最终模型只有3.5M，可识别6622个汉字；2.8M模型可识别63个字母数字符号同时发布了几种预训练的中英文识别模型，包括文本检测器(97K幅图像)、方向分类器(600K幅图像)和文本识别器(179M幅图像)。

The Optical Character Recognition (OCR) systems have been widely used in various of application scenarios, such as office automation (OA) systems, factory automations, online educations, map productions etc. However, OCR is still a challenging task due to the various of text appearances and the demand of computational efficiency. In this paper, we propose a practical ultra lightweight OCR system, i.e., PP-OCR. The overall model size of the PP-OCR is only 3.5M for recognizing 6622 Chinese characters and 2.8M for recognizing 63 alphanumeric symbols, respectively. We introduce a bag of strategies to either enhance the model ability or reduce the model size. The corresponding ablation experiments with the real data are also provided. Meanwhile, several pre-trained models for the Chinese and English recognition are released, including a text detector (97K images are used), a direction classifier (600K images are used) as well as a text recognizer (17.9M images are used). Besides, the proposed PP-OCR are also verified in several other language recognition tasks, including French, Korean, Japanese and German. All of the above mentioned models are open-sourced and the codes are available in the GitHub repository, i.e., this https URL.

https://weibo.com/1402400261/JmF0HbzBc

5、[CV] Learning Unseen Emotions from Gestures via Semantically-Conditioned Zero-Shot Perception with Adversarial Autoencoders

A Banerjee, U Bhattacharya, A Bera [University of Maryland]从姿态序列感知情绪的零样本学习架构(SC-AAE)，用对抗损失来学习姿态和情绪词的语义条件空间之间的映射，将姿态映射到训练时没见过的新情绪类别。

提出了一种相对的、基于自编码器的表示学习，用word2vec嵌入将3D动作捕获的姿态序列与自然语言感知的情感术语的向量化表示关联起来语言语义嵌入提供了情绪标签空间的表示，用这种潜在分布将姿态序列映射到适当的分类情绪标签。

We present a novel generalized zero-shot algorithm to recognize perceived emotions from gestures. Our task is to map gestures to novel emotion categories not encountered in training. We introduce an adversarial, autoencoder-based representation learning that correlates 3D motion-captured gesture sequence with the vectorized representation of the natural-language perceived emotion terms using word2vec embeddings. The language-semantic embedding provides a representation of the emotion label space, and we leverage this underlying distribution to map the gesture-sequences to the appropriate categorical emotion labels. We train our method using a combination of gestures annotated with known emotion terms and gestures not annotated with any emotions. We evaluate our method on the MPI Emotional Body Expressions Database (EBEDB) and obtain an accuracy of 58.43%. This improves the performance of current state-of-the-art algorithms for generalized zero-shot learning by 25--27% on the absolute.

https://weibo.com/1402400261/JmF6hyP22

免责声明：本站所有信息均搜集自互联网，并不代表本站观点，本站不对其真实合法性负责。如有信息侵犯了您的权益，请告知，本站将立刻处理。联系QQ：1640731186