Ai Magazine最新文献

{"title":"Deceptively simple: An outsider's perspective on natural language processing","authors":"Ashiqur R. KhudaBukhsh","doi":"10.1002/aaai.12204","DOIUrl":"https://doi.org/10.1002/aaai.12204","url":null,"abstract":"<p>This article highlights a collection of ideas with an underlying deceptive simplicity that addresses several practical challenges in computational social science and generative AI safety. These ideas lead to (1) an interpretable and quantifiable framework for political polarization; (2) a language identifier robust to noisy social media text settings; (3) a cross-lingual semantic sampler that harnesses code-switching; and (4) a bias audit framework that uncovers shocking racism, antisemitism, misogyny, and other biases in a wide suite of large language models.</p>","PeriodicalId":7854,"journal":{"name":"Ai Magazine","volume":"45 4","pages":"569-582"},"PeriodicalIF":2.5,"publicationDate":"2024-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aaai.12204","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142861857","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AI-assisted research collaboration with open data for fair and effective response to call for proposals","authors":"Siva Likitha Valluru,&nbsp;Michael Widener,&nbsp;Biplav Srivastava,&nbsp;Sriraam Natarajan,&nbsp;Sugata Gangopadhyay","doi":"10.1002/aaai.12203","DOIUrl":"https://doi.org/10.1002/aaai.12203","url":null,"abstract":"<p>Building teams and promoting collaboration are two very common business activities. An example of these are seen in the <i>TeamingForFunding</i> problem, where research institutions and researchers are interested to identify collaborative opportunities when applying to funding agencies in response to latter's calls for proposals. We describe a novel <i>deployed</i> system to recommend teams using a variety of Artificial Intelligence (AI) methods, such that (1) each team achieves the highest possible skill coverage that is demanded by the opportunity, and (2) the workload of distributing the opportunities is balanced among the candidate members. We address these questions by extracting skills latent in open data of proposal calls (demand) and researcher profiles (supply), normalizing them using taxonomies, and creating efficient algorithms that match demand to supply. We create teams to maximize goodness along a novel metric balancing short- and long-term objectives. We evaluate our system in two diverse settings in US and India of researchers and proposal calls, at two different time instants about 1 year apart (total 4 settings), to establish generality of our approach, and deploy it at a major US university. We validate the effectiveness of our algorithms (1) quantitatively, by evaluating the recommended teams using a goodness score and find that more informed methods lead to recommendations of smaller number of teams and higher goodness, and (2) qualitatively, by conducting a large-scale user study at a college-wide level, and demonstrate that users overall found the tool very useful and relevant.</p>","PeriodicalId":7854,"journal":{"name":"Ai Magazine","volume":"45 4","pages":"457-471"},"PeriodicalIF":2.5,"publicationDate":"2024-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aaai.12203","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142861856","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Learning representations for robust human–robot interaction","authors":"Yen-Ling Kuo","doi":"10.1002/aaai.12197","DOIUrl":"https://doi.org/10.1002/aaai.12197","url":null,"abstract":"<p>This article summarizes the author's presentation in the New Faculty Highlight at the Thirty-Eighth AAAI Conference on Artificial Intelligence. It discusses the desired properties of representations for enabling robust human–robot interaction. Examples from the author's work are presented to show how to build these properties into models for performing tasks with natural language guidance and engaging in social interactions with other agents.</p>","PeriodicalId":7854,"journal":{"name":"Ai Magazine","volume":"45 4","pages":"561-568"},"PeriodicalIF":2.5,"publicationDate":"2024-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aaai.12197","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142851503","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Fusing remote and social sensing data for flood impact mapping","authors":"Zainab Akhtar,&nbsp;Umair Qazi,&nbsp;Aya El-Sakka,&nbsp;Rizwan Sadiq,&nbsp;Ferda Ofli,&nbsp;Muhammad Imran","doi":"10.1002/aaai.12196","DOIUrl":"https://doi.org/10.1002/aaai.12196","url":null,"abstract":"<p>The absence of comprehensive situational awareness information poses a significant challenge for humanitarian organizations during their response efforts. We present Flood Insights, an end-to-end system, that ingests data from multiple nontraditional data sources such as remote sensing, social sensing, and geospatial data. We employ state-of-the-art natural language processing and computer vision models to identify flood exposure, ground-level damage and flood reports, and most importantly, urgent needs of affected people. We deploy and test the system during a recent real-world catastrophe, the 2022 Pakistan floods, to surface critical situational and damage information at the district level. We validated the system's effectiveness through various statistical analyses using official ground-truth data, showcasing its strong performance and explanatory power of integrating multiple data sources. Moreover, the system was commended by the United Nations Development Programme stationed in Pakistan, as well as local authorities, for pinpointing hard-hit districts and enhancing disaster response.</p>","PeriodicalId":7854,"journal":{"name":"Ai Magazine","volume":"45 4","pages":"486-501"},"PeriodicalIF":2.5,"publicationDate":"2024-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aaai.12196","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142861676","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A survey of out-of-distribution generalization for graph machine learning from a causal view","authors":"Jing Ma","doi":"10.1002/aaai.12202","DOIUrl":"https://doi.org/10.1002/aaai.12202","url":null,"abstract":"<p>Graph machine learning (GML) has been successfully applied across a wide range of tasks. Nonetheless, GML faces significant challenges in generalizing over out-of-distribution (OOD) data, which raises concerns about its wider applicability. Recent advancements have underscored the crucial role of causality-driven approaches in overcoming these generalization challenges. Distinct from traditional GML methods that primarily rely on statistical dependencies, causality-focused strategies delve into the underlying causal mechanisms of data generation and model prediction, thus significantly improving the generalization of GML across different environments. This paper offers a thorough review of recent progress in causality-involved GML generalization. We elucidate the fundamental concepts of employing causality to enhance graph model generalization and categorize the various approaches, providing detailed descriptions of their methodologies and the connections among them. Furthermore, we explore the incorporation of causality in other related important areas of trustworthy GML, such as explanation, fairness, and robustness. Concluding with a discussion on potential future research directions, this review seeks to articulate the continuing development and future potential of causality in enhancing the trustworthiness of GML.</p>","PeriodicalId":7854,"journal":{"name":"Ai Magazine","volume":"45 4","pages":"537-548"},"PeriodicalIF":2.5,"publicationDate":"2024-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aaai.12202","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142851524","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The virtual driving instructor: Multi-agent system collaborating via knowledge graph for scalable driver education","authors":"Johannes Rehm,&nbsp;Irina Reshodko,&nbsp;Stian Zimmermann Børresen,&nbsp;Odd Erik Gundersen","doi":"10.1002/aaai.12201","DOIUrl":"https://doi.org/10.1002/aaai.12201","url":null,"abstract":"<p>This work introduces the design, development, and deployment of a virtual driving instructor (VDI) for enhanced driver education. The VDI provides personalized, real-time feedback to students in a driving simulator, addressing some of the limitations of traditional driver instruction. Employing a hybrid AI system, the VDI combines rule-based agents, learning-based agents, knowledge graphs, and Bayesian networks to assess and monitor student performance in a comprehensive manner. Implemented in multiple simulators at a driving school in Norway, the system aims to leverage AI and driving simulation to improve both the learning experience and the efficiency of instruction. Initial feedback from students has been largely positive, highlighting the effectiveness of this integration while also pointing to areas for further improvement. This marks a significant stride in infusing technology into driver education, offering a scalable and efficient approach to instruction.</p>","PeriodicalId":7854,"journal":{"name":"Ai Magazine","volume":"45 4","pages":"514-525"},"PeriodicalIF":2.5,"publicationDate":"2024-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aaai.12201","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142851523","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Framework to enable and test conversational assistant for APIs and RPAs","authors":"Jayachandu Bandlamudi,&nbsp;Kushal Mukherjee,&nbsp;Prerna Agarwal,&nbsp;Ritwik Chaudhuri,&nbsp;Rakesh Pimplikar,&nbsp;Sampath Dechu,&nbsp;Alex Straley,&nbsp;Anbumunee Ponniah,&nbsp;Renuka Sindhgatta","doi":"10.1002/aaai.12198","DOIUrl":"https://doi.org/10.1002/aaai.12198","url":null,"abstract":"<p>In the realm of business automation, conversational assistants are emerging as the primary method for making automation software accessible to users in various business sectors. Access to automation primarily occurs through application programming interface (APIs) and robotic process automation (RPAs). To effectively convert APIs and RPAs into chatbots on a larger scale, it is crucial to establish an automated process for generating data and training models that can recognize user intentions, identify questions for conversational slot filling, and provide recommendations for subsequent actions. In this paper, we present a technique for enhancing and generating natural language conversational artifacts from API specifications using large language models (LLMs). The goal is to utilize LLMs in the “build” phase to assist humans in creating skills for digital assistants. As a result, the system does not need to rely on LLMs during conversations with business users, leading to efficient deployment. Along with enabling digital assistants, our system employs LLMs as proxies to simulate human interaction and automatically evaluate the digital assistant's performance. Experimental results highlight the effectiveness of our proposed approach. Our system is deployed in the IBM Watson Orchestrate product for general availability.</p>","PeriodicalId":7854,"journal":{"name":"Ai Magazine","volume":"45 4","pages":"443-456"},"PeriodicalIF":2.5,"publicationDate":"2024-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aaai.12198","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142851522","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Data-efficient graph learning: Problems, progress, and prospects","authors":"Kaize Ding,&nbsp;Yixin Liu,&nbsp;Chuxu Zhang,&nbsp;Jianling Wang","doi":"10.1002/aaai.12200","DOIUrl":"https://doi.org/10.1002/aaai.12200","url":null,"abstract":"<p>Graph-structured data, ranging from social networks to financial transaction networks, from citation networks to gene regulatory networks, have been widely used for modeling a myriad of real-world systems. As a prevailing model architecture to model graph-structured data, graph neural networks (GNNs) have drawn much attention in both academic and industrial communities in the past decades. Despite their success in different graph learning tasks, existing methods usually rely on learning from “big” data, requiring a large amount of labeled data for model training. However, it is common that real-world graphs are associated with “small” labeled data as data annotation and labeling on graphs is always time and resource-consuming. Therefore, it is imperative to investigate graph machine learning (graph ML) with low-cost human supervision for low-resource settings where limited or even no labeled data is available. This paper investigates a new research field—data-efficient graph learning, which aims to push forward the performance boundary of graph ML models with different kinds of low-cost supervision signals. Specifically, we outline the fundamental research problems, review the current progress, and discuss the future prospects of data-efficient graph learning, aiming to illuminate the path for subsequent research in this field.</p>","PeriodicalId":7854,"journal":{"name":"Ai Magazine","volume":"45 4","pages":"549-560"},"PeriodicalIF":2.5,"publicationDate":"2024-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aaai.12200","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142861732","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DCV\u0000 2\u0000 \u0000 I\u0000 \u0000 $text{DCV}^2text{I}$\u0000 : Leveraging deep vision models to support geographers' visual interpretation in dune segmentation","authors":"Anqi Lu,&nbsp;Zifeng Wu,&nbsp;Zheng Jiang,&nbsp;Wei Wang,&nbsp;Eerdun Hasi,&nbsp;Yi Wang","doi":"10.1002/aaai.12199","DOIUrl":"https://doi.org/10.1002/aaai.12199","url":null,"abstract":"<p>Visual interpretation is extremely important in human geography as the primary technique for geographers to use photograph data in identifying, classifying, and quantifying geographic and topological objects or regions. However, it is also time-consuming and requires overwhelming manual effort from professional geographers. This paper describes our interdisciplinary team's efforts in integrating computer vision models with geographers' visual image interpretation process to reduce their workload in interpreting images. Focusing on the dune segmentation task, we proposed an approach called <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <msup>\u0000 <mi>DCV</mi>\u0000 <mn>2</mn>\u0000 </msup>\u0000 <mi>I</mi>\u0000 </mrow>\u0000 <annotation>${bf DCV}^2{bf I}$</annotation>\u0000 </semantics></math> featuring a deep dune segmentation model to identify dunes and label their ranges in an automated way. By developing a tool to connect our model with ArcGIS—one of the most popular workbenches for visual interpretation, geographers can further refine the automatically generated dune segmentation on images without learning any CV or deep learning techniques. Our approach thus realized a noninvasive change to geographers' visual interpretation routines, reducing their manual efforts while incurring minimal interruptions to their work routines and tools they are familiar with. Deployment with a leading Chinese geography research institution demonstrated the potential of <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <msup>\u0000 <mi>DCV</mi>\u0000 <mn>2</mn>\u0000 </msup>\u0000 <mi>I</mi>\u0000 </mrow>\u0000 <annotation>${bf DCV}^2{bf I}$</annotation>\u0000 </semantics></math> in supporting geographers in researching and solving drylands desertification.</p>","PeriodicalId":7854,"journal":{"name":"Ai Magazine","volume":"45 4","pages":"472-485"},"PeriodicalIF":2.5,"publicationDate":"2024-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aaai.12199","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142861675","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A submodular optimization approach to trustworthy loan approval automation","authors":"Kyungsik Lee,&nbsp;Hana Yoo,&nbsp;Sumin Shin,&nbsp;Wooyoung Kim,&nbsp;Yeonung Baek,&nbsp;Hyunjin Kang,&nbsp;Jaehyun Kim,&nbsp;Kee-Eung Kim","doi":"10.1002/aaai.12195","DOIUrl":"https://doi.org/10.1002/aaai.12195","url":null,"abstract":"<p>In the field of finance, the underwriting process is an essential step in evaluating every loan application. During this stage, the borrowers' creditworthiness and ability to repay the loan are assessed to ultimately decide whether to approve the loan application. One of the core components of underwriting is credit scoring, in which the probability of default is estimated. As such, there has been significant progress in enhancing the predictive accuracy of credit scoring models through the use of machine learning, but there still exists a need to ultimately construct an approval rule that takes into consideration additional criteria beyond the score itself. This construction process is traditionally done manually to ensure that the approval rule remains interpretable to humans. In this paper, we outline an automated system for optimizing a rule-based system for approving loan applications, which has been deployed at Hyundai Capital Services (HCS). The main challenge lays in creating a high-quality rule base that is simultaneously simple enough to be interpretable by risk analysts as well as customers, since the approval decision should be easily understandable. We addressed this challenge through principled submodular optimization. The deployment of our system has led to a 14% annual growth in the volume of loan services at HCS, while maintaining the target bad rate, and has resulted in the approval of customers who might have otherwise been rejected.</p>","PeriodicalId":7854,"journal":{"name":"Ai Magazine","volume":"45 4","pages":"502-513"},"PeriodicalIF":2.5,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aaai.12195","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142859946","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}