发布求助
文献互助 智能选刊 最新文献

AI Communications最新文献

筛选
英文 中文
Optimizing human hand gestures for AI-systems 为人工智能系统优化人类手势
IF 0.8 4区 计算机科学
AI Communications Pub Date : 2022-05-06 DOI: 10.3233/aic-210081
Johannes Schneider
{"title":"Optimizing human hand gestures for AI-systems","authors":"Johannes Schneider","doi":"10.3233/aic-210081","DOIUrl":"https://doi.org/10.3233/aic-210081","url":null,"abstract":"Humans interact more and more with systems containing AI components. In this work, we focus on hand gestures such as handwriting and sketches serving as inputs to such systems. They are represented as a trajectory, i.e. sequence of points, that is altered to improve interaction with an AI model while keeping the model fixed. Optimized inputs are accompanied by instructions on how to create them. We aim to cut on effort for humans and recognition errors while limiting changes to original inputs. We derive multiple objectives and measures and propose continuous and discrete optimization methods embracing the AI model to improve samples in an iterative fashion by removing, shifting and reordering points of the gesture trajectory. Our quantitative and qualitative evaluation shows that mimicking generated proposals that differ only modestly from the original ones leads to lower error rates and requires less effort. Furthermore, our work can be easily adjusted for sketch abstraction improving on prior work.","PeriodicalId":50835,"journal":{"name":"AI Communications","volume":"20 1","pages":"153-169"},"PeriodicalIF":0.8,"publicationDate":"2022-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79282603","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Leveraging external resources for offensive content detection in social media 利用外部资源检测社交媒体中的攻击性内容
IF 0.8 4区 计算机科学
AI Communications Pub Date : 2022-05-04 DOI: 10.3233/aic-210138
György Kovács, Pedro Alonso, Rajkumar Saini, M. Liwicki
{"title":"Leveraging external resources for offensive content detection in social media","authors":"György Kovács, Pedro Alonso, Rajkumar Saini, M. Liwicki","doi":"10.3233/aic-210138","DOIUrl":"https://doi.org/10.3233/aic-210138","url":null,"abstract":"Hate speech is a burning issue of today’s society that cuts across numerous strategic areas, including human rights protection, refugee protection, and the fight against racism and discrimination. The gravity of the subject is further demonstrated by António Guterres, the United Nations Secretary-General, calling it “a menace to democratic values, social stability, and peace”. One central platform for the spread of hate speech is the Internet and social media in particular. Thus, automatic detection of hateful and offensive content on these platforms is a crucial challenge that would strongly contribute to an equal and sustainable society when overcome. One significant difficulty in meeting this challenge is collecting sufficient labeled data. In our work, we examine how various resources can be leveraged to circumvent this difficulty. We carry out extensive experiments to exploit various data sources using different machine learning models, including state-of-the-art transformers. We have found that using our proposed methods, one can attain state-of-the-art performance detecting hate speech on Twitter (outperforming the winner of both the HASOC 2019 and HASOC 2020 competitions). It is observed that in general, adding more data improves the performance or does not decrease it. Even when using good language models and knowledge transfer mechanisms, the best results were attained using data from one or two additional data sets.","PeriodicalId":50835,"journal":{"name":"AI Communications","volume":"35 1","pages":"87-109"},"PeriodicalIF":0.8,"publicationDate":"2022-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87035283","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
A cross-lingual sentence pair interaction feature capture model based on pseudo-corpus and multilingual embedding 基于伪语料库和多语言嵌入的跨语言句子对交互特征捕获模型
IF 0.8 4区 计算机科学
AI Communications Pub Date : 2022-04-13 DOI: 10.3233/aic-210085
Gang Liu, Yichao Dong, Kai Wang, Zhizheng Yan
{"title":"A cross-lingual sentence pair interaction feature capture model based on pseudo-corpus and multilingual embedding","authors":"Gang Liu, Yichao Dong, Kai Wang, Zhizheng Yan","doi":"10.3233/aic-210085","DOIUrl":"https://doi.org/10.3233/aic-210085","url":null,"abstract":"Recently, the emergence of the digital language division and the availability of cross-lingual benchmarks make researches of cross-lingual texts more popular. However, the performance of existing methods based on mapping relation are not good enough, because sometimes the structures of language spaces are not isomorphic. Besides, polysemy makes the extraction of interaction features hard. For cross-lingual word embedding, a model named Cross-lingual Word Embedding Space Based on Pseudo Corpus (CWE-PC) is proposed to obtain cross-lingual and multilingual word embedding. For cross-lingual sentence pair interaction feature capture, a Cross-language Feature Capture Based on Similarity Matrix (CFC-SM) model is built to extract cross-lingual interaction features. ELMo pretrained model and multiple layer convolution are used to alleviate polysemy and extract interaction features. These models are evaluated on multiple language pairs and results show that they outperform the state-of-the-art cross-lingual word embedding methods.","PeriodicalId":50835,"journal":{"name":"AI Communications","volume":"11 1","pages":"1-14"},"PeriodicalIF":0.8,"publicationDate":"2022-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72543174","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Multi-scale redistribution feature pyramid for object detection 用于目标检测的多尺度再分布特征金字塔
IF 0.8 4区 计算机科学
AI Communications Pub Date : 2022-04-04 DOI: 10.3233/aic-210222
Huifang Qian, Jiahao Guo, Xuan Zhou
{"title":"Multi-scale redistribution feature pyramid for object detection","authors":"Huifang Qian, Jiahao Guo, Xuan Zhou","doi":"10.3233/aic-210222","DOIUrl":"https://doi.org/10.3233/aic-210222","url":null,"abstract":"Many feature pyramid models now use simple contextual feature aggregation, which does not make full use of the semantic information of multi-scale features. Therefore, Multi-scale Redistribution Feature Pyramid Network (MRFPN) is proposed. In order to strengthen feature fusion and solve the two problems of feature redundancy and high abstraction, modified-BiFPN is designed. The features output by the modified-BiFPN module are semantically balanced through the balanced feature map, so as to alleviate the semantic differences between multi-scales. Then a new channel attention module is proposed, which realizes the multi-scale association of the feature information fused to the balanced feature map. Finally, a new feature pyramid is formed through the residual edge for prediction. MRFPN have been evaluated on PASCAL VOC 2012 dataset and MS COCO dataset, which has higher detection accuracy compared with other state-of-the-art detectors.","PeriodicalId":50835,"journal":{"name":"AI Communications","volume":"31 1","pages":"15-30"},"PeriodicalIF":0.8,"publicationDate":"2022-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85445641","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
The CADE-28 Automated Theorem Proving System Competition – CASC-28 CADE-28自动定理证明系统竞赛——CASC-28
IF 0.8 4区 计算机科学
AI Communications Pub Date : 2022-03-18 DOI: 10.3233/aic-210235
G. Sutcliffe, Martin Desharnais
{"title":"The CADE-28 Automated Theorem Proving System Competition – CASC-28","authors":"G. Sutcliffe, Martin Desharnais","doi":"10.3233/aic-210235","DOIUrl":"https://doi.org/10.3233/aic-210235","url":null,"abstract":"The CADE ATP System Competition (CASC) is the annual evaluation of fully automatic, classical logic Automated Theorem Proving (ATP) systems. CASC-28 was the twenty-sixth competition in the CASC series. Twenty-two ATP systems competed in the various competition divisions. This paper presents an outline of the competition design and a commentated summary of the results.","PeriodicalId":50835,"journal":{"name":"AI Communications","volume":"1 1","pages":""},"PeriodicalIF":0.8,"publicationDate":"2022-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42076858","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Special issue on historical and future perspectives of AI 关于人工智能的历史和未来观点的特刊
IF 0.8 4区 计算机科学
AI Communications Pub Date : 2022-03-04 DOI: 10.3233/aic-229001
S. Schockaert, R. Peñaloza
{"title":"Special issue on historical and future perspectives of AI","authors":"S. Schockaert, R. Peñaloza","doi":"10.3233/aic-229001","DOIUrl":"https://doi.org/10.3233/aic-229001","url":null,"abstract":"In its role as the European Journal on Artificial Intelligence, AI Communications strives to showcase high quality research developed in Europe. Under this premise, we invited contributions reflecting historical and future perspectives of AI. This issue is the result of such invitations. The papers appearing in this issue are as heterogeneous as the whole Artificial Intelligence field. The first paper deals with the very current issue of accountability in AI. With a view towards the future of AI, the paper provides an accountability ecosystem, taking into account lessons learned from recent industrial AI systems and their drawbacks. The second paper analyses the current trends in the area of Neuro-Symbolic AI. Although the general area of Neuro-Symbolic integration has been around for over two decades, it has only very recently become a main-stream topic, as attested by the number of submissions in top AI-related conferences. The third paper makes a connection between recent formalisations of analogical reasoning, on the one hand, and the historical treatment of numerical proportions, on the other hand. We are very aware that there are many historical and future perspectives of AI that are not covered in this issue. Our hope is that these papers will spark a larger conversation.","PeriodicalId":50835,"journal":{"name":"AI Communications","volume":"64 1","pages":"179"},"PeriodicalIF":0.8,"publicationDate":"2022-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87027846","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Emergent behaviours in multi-agent systems with Evolutionary Game Theory 基于进化博弈论的多智能体系统的突发行为
IF 0.8 4区 计算机科学
AI Communications Pub Date : 2022-01-01 DOI: 10.3233/AIC-220104
H. Anh
{"title":"Emergent behaviours in multi-agent systems with Evolutionary Game Theory","authors":"H. Anh","doi":"10.3233/AIC-220104","DOIUrl":"https://doi.org/10.3233/AIC-220104","url":null,"abstract":"","PeriodicalId":50835,"journal":{"name":"AI Communications","volume":"35 1","pages":"327-337"},"PeriodicalIF":0.8,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69734323","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Boosting branch-and-bound MaxSAT solvers with clause learning 用子句学习增强分支定界MaxSAT求解器
IF 0.8 4区 计算机科学
AI Communications Pub Date : 2021-12-23 DOI: 10.3233/aic-210178
Chu Min Li, Zhenxing Xu, Jordi Coll, F. Manyà, Djamal Habet, Kun He
{"title":"Boosting branch-and-bound MaxSAT solvers with clause learning","authors":"Chu Min Li, Zhenxing Xu, Jordi Coll, F. Manyà, Djamal Habet, Kun He","doi":"10.3233/aic-210178","DOIUrl":"https://doi.org/10.3233/aic-210178","url":null,"abstract":"The Maximum Satisfiability Problem, or MaxSAT, offers a suitable problem solving formalism for combinatorial optimization problems. Nevertheless, MaxSAT solvers implementing the Branch-and-Bound (BnB) scheme have not succeeded in solving challenging real-world optimization problems. It is widely believed that BnB MaxSAT solvers are only superior on random and some specific crafted instances. At the same time, SAT-based MaxSAT solvers perform particularly well on real-world instances. To overcome this shortcoming of BnB MaxSAT solvers, this paper proposes a new BnB MaxSAT solver called MaxCDCL. The main feature of MaxCDCL is the combination of clause learning of soft conflicts and an efficient bounding procedure. Moreover, the paper reports on an experimental investigation showing that MaxCDCL is competitive when compared with the best performing solvers of the 2020 MaxSAT Evaluation. MaxCDCL performs very well on real-world instances, and solves a number of instances that other solvers cannot solve. Furthermore, MaxCDCL, when combined with the best performing MaxSAT solvers, solves the highest number of instances of a collection from all the MaxSAT evaluations held so far.","PeriodicalId":50835,"journal":{"name":"AI Communications","volume":"35 1","pages":"131-151"},"PeriodicalIF":0.8,"publicationDate":"2021-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81309327","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 5
Pruning by leveraging training dynamics 通过利用训练动态来修剪
IF 0.8 4区 计算机科学
AI Communications Pub Date : 2021-11-04 DOI: 10.3233/aic-210127
Andrei C. Apostol, M. Stol, P. Forré
{"title":"Pruning by leveraging training dynamics","authors":"Andrei C. Apostol, M. Stol, P. Forré","doi":"10.3233/aic-210127","DOIUrl":"https://doi.org/10.3233/aic-210127","url":null,"abstract":"We propose a novel pruning method which uses the oscillations around 0, i.e. sign flips, that a weight has undergone during training in order to determine its saliency. Our method can perform pruning before the network has converged, requires little tuning effort due to having good default values for its hyperparameters, and can directly target the level of sparsity desired by the user. Our experiments, performed on a variety of object classification architectures, show that it is competitive with existing methods and achieves state-of-the-art performance for levels of sparsity of 99.6 % and above for 2 out of 3 of the architectures tested. Moreover, we demonstrate that our method is compatible with quantization, another model compression technique. For reproducibility, we release our code at https://github.com/AndreiXYZ/flipout.","PeriodicalId":50835,"journal":{"name":"AI Communications","volume":"24 1","pages":"65-85"},"PeriodicalIF":0.8,"publicationDate":"2021-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74726354","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Explaining transformer-based image captioning models: An empirical analysis 解释基于变压器的图像字幕模型:一个实证分析
IF 0.8 4区 计算机科学
AI Communications Pub Date : 2021-10-29 DOI: 10.3233/aic-210172
M. Cornia, L. Baraldi, R. Cucchiara
{"title":"Explaining transformer-based image captioning models: An empirical analysis","authors":"M. Cornia, L. Baraldi, R. Cucchiara","doi":"10.3233/aic-210172","DOIUrl":"https://doi.org/10.3233/aic-210172","url":null,"abstract":"Image Captioning is the task of translating an input image into a textual description. As such, it connects Vision and Language in a generative fashion, with applications that range from multi-modal search engines to help visually impaired people. Although recent years have witnessed an increase in accuracy in such models, this has also brought increasing complexity and challenges in interpretability and visualization. In this work, we focus on Transformer-based image captioning models and provide qualitative and quantitative tools to increase interpretability and assess the grounding and temporal alignment capabilities of such models. Firstly, we employ attribution methods to visualize what the model concentrates on in the input image, at each step of the generation. Further, we propose metrics to evaluate the temporal alignment between model predictions and attribution scores, which allows measuring the grounding capabilities of the model and spot hallucination flaws. Experiments are conducted on three different Transformer-based architectures, employing both traditional and Vision Transformer-based visual features.","PeriodicalId":50835,"journal":{"name":"AI Communications","volume":"16 1","pages":"111-129"},"PeriodicalIF":0.8,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88031420","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 12
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：481959085
Book学术官方微信