Artificial Intelligence最新文献_第8页

A domain-independent agent architecture for adaptive operation in evolving open worlds 在不断进化的开放世界中实现自适应运行的独立于领域的代理架构

IF 14.4 2区计算机科学

Artificial Intelligence Pub Date : 2024-06-06 DOI: 10.1016/j.artint.2024.104161

Shiwali Mohan , Wiktor Piotrowski , Roni Stern , Sachin Grover , Sookyung Kim , Jacob Le , Yoni Sher , Johan de Kleer

{"title":"A domain-independent agent architecture for adaptive operation in evolving open worlds","authors":"Shiwali Mohan , Wiktor Piotrowski , Roni Stern , Sachin Grover , Sookyung Kim , Jacob Le , Yoni Sher , Johan de Kleer","doi":"10.1016/j.artint.2024.104161","DOIUrl":"https://doi.org/10.1016/j.artint.2024.104161","url":null,"abstract":"<div><p> Model-based reasoning agents are ill-equipped to act in novel situations in which their model of the environment no longer sufficiently represents the world. We propose HYDRA, a framework for designing model-based agents operating in mixed discrete-continuous worlds that can autonomously detect when the environment has evolved from its canonical setup, understand how it has evolved, and adapt the agents' models to perform effectively. HYDRA is based upon PDDL+, a rich modeling language for planning in mixed, discrete-continuous environments. It augments the planning module with visual reasoning, task selection, and action execution modules for closed-loop interaction with complex environments. HYDRA implements a novel meta-reasoning process that enables the agent to monitor its own behavior from a variety of aspects. The process employs a diverse set of computational methods to maintain expectations about the agent's own behavior in an environment. Divergences from those expectations are useful in detecting when the environment has evolved and identifying opportunities to adapt the underlying models. HYDRA builds upon ideas from diagnosis and repair and uses a heuristics-guided search over model changes such that they become competent in novel conditions. The HYDRA framework has been used to implement <em>novelty-aware</em> agents for three diverse domains - CartPole++ (a higher dimension variant of a classic control problem), Science Birds (an IJCAI competition problem<span><sup>1</sup></span>), and PogoStick (a specific problem domain in Minecraft). We report empirical observations from these domains to demonstrate the efficacy of various components in the novelty meta-reasoning process.</p></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"334 ","pages":"Article 104161"},"PeriodicalIF":14.4,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141303042","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Functional Relation Field: A Model-Agnostic Framework for Multivariate Time Series Forecasting 功能关系场：多变量时间序列预测的模型诊断框架

IF 14.4 2区计算机科学

Artificial Intelligence Pub Date : 2024-06-05 DOI: 10.1016/j.artint.2024.104158

Ting Li , Bing Yu , Jianguo Li , Zhanxing Zhu

{"title":"Functional Relation Field: A Model-Agnostic Framework for Multivariate Time Series Forecasting","authors":"Ting Li , Bing Yu , Jianguo Li , Zhanxing Zhu","doi":"10.1016/j.artint.2024.104158","DOIUrl":"https://doi.org/10.1016/j.artint.2024.104158","url":null,"abstract":"<div><p>In multivariate time series forecasting, the most popular strategy for modeling the relationship between multiple time series is the construction of graph, where each time series is represented as a node and related nodes are connected by edges. However, the relationship between multiple time series is typically complicated, e.g. the sum of outflows from upstream nodes may be equal to the inflows of downstream nodes. Such relations widely exist in many real-world scenarios for multivariate time series forecasting, yet are far from well studied. In these cases, graph might be insufficient for modeling the complex dependency between nodes. To this end, we explore a new framework to model the inter-node relationship in a more precise way based our proposed inductive bias, <em>Functional Relation Field</em>, where a group of functions parameterized by neural networks are learned to characterize the dependency between multiple time series. Essentially, these learned functions then form a “field”, i.e. a particular set of constraints, to regularize the training loss of the backbone prediction network and enforce the inference process to satisfy these constraints. Since our framework introduces the relationship bias in a data-driven manner, it is flexible and model-agnostic such that it can be applied to any existing multivariate time series prediction networks for boosting performance. The experiment is conducted on one toy dataset to show our approach can well recover the true constraint relationship between nodes. And various real-world datasets are also considered with different backbone prediction networks. Results show that the prediction error can be reduced remarkably with the aid of the proposed framework.</p></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"334 ","pages":"Article 104158"},"PeriodicalIF":14.4,"publicationDate":"2024-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0004370224000948/pdfft?md5=1e0e8c2dca5cc80e5c38837feded9d5f&pid=1-s2.0-S0004370224000948-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141308373","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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}

引用次数: 0

Stability based on single-agent deviations in additively separable hedonic games 基于可加可分对冲博弈中单代理偏差的稳定性

IF 14.4 2区计算机科学

Artificial Intelligence Pub Date : 2024-05-31 DOI: 10.1016/j.artint.2024.104160

Felix Brandt , Martin Bullinger , Leo Tappe

{"title":"Stability based on single-agent deviations in additively separable hedonic games","authors":"Felix Brandt , Martin Bullinger , Leo Tappe","doi":"10.1016/j.artint.2024.104160","DOIUrl":"https://doi.org/10.1016/j.artint.2024.104160","url":null,"abstract":"<div><p>Coalition formation is a central concern in multiagent systems. A common desideratum for coalition structures is stability, defined by the absence of beneficial deviations of single agents. Such deviations require an agent to improve her utility by joining another coalition. On top of that, the feasibility of deviations may also be restricted by demanding consent of agents in the welcoming and/or the abandoned coalition. While most of the literature focuses on deviations constrained by unanimous consent, we also study consent decided by majority vote and introduce two new stability notions that can be seen as local variants of another solution concept called popularity. We investigate stability in additively separable hedonic games by pinpointing boundaries to computational complexity depending on the type of consent and friend-oriented utility restrictions. The latter restrictions shed new light on well-studied classes of games based on the appreciation of friends or the aversion to enemies. Many of our positive results follow from a new combinatorial observation that we call the <em>Deviation Lemma</em> and that we leverage to prove the convergence of simple and natural single-agent dynamics under fairly general conditions. Our negative results, in particular, resolve the complexity of contractual Nash stability in additively separable hedonic games.</p></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"334 ","pages":"Article 104160"},"PeriodicalIF":14.4,"publicationDate":"2024-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0004370224000961/pdfft?md5=e987438fd09ba66fd8cb7e8db197482a&pid=1-s2.0-S0004370224000961-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141244960","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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}

引用次数: 0

Joint learning of reward machines and policies in environments with partially known semantics 在部分已知语义的环境中联合学习奖赏机和策略

IF 14.4 2区计算机科学

Artificial Intelligence Pub Date : 2024-05-23 DOI: 10.1016/j.artint.2024.104146

Christos K. Verginis , Cevahir Koprulu , Sandeep Chinchali , Ufuk Topcu

{"title":"Joint learning of reward machines and policies in environments with partially known semantics","authors":"Christos K. Verginis , Cevahir Koprulu , Sandeep Chinchali , Ufuk Topcu","doi":"10.1016/j.artint.2024.104146","DOIUrl":"10.1016/j.artint.2024.104146","url":null,"abstract":"<div><p>We study the problem of reinforcement learning for a task encoded by a reward machine. The task is defined over a set of properties in the environment, called atomic propositions, and represented by Boolean variables. One unrealistic assumption commonly used in the literature is that the truth values of these propositions are accurately known. In real situations, however, these truth values are uncertain since they come from sensors that suffer from imperfections. At the same time, reward machines can be difficult to model explicitly, especially when they encode complicated tasks. We develop a reinforcement-learning algorithm that infers a reward machine that encodes the underlying task while learning how to execute it, despite the uncertainties of the propositions' truth values. In order to address such uncertainties, the algorithm maintains a probabilistic estimate about the truth value of the atomic propositions; it updates this estimate according to new sensory measurements that arrive from exploration of the environment. Additionally, the algorithm maintains a hypothesis reward machine, which acts as an estimate of the reward machine that encodes the task to be learned. As the agent explores the environment, the algorithm updates the hypothesis reward machine according to the obtained rewards and the estimate of the atomic propositions' truth value. Finally, the algorithm uses a Q-learning procedure for the states of the hypothesis reward machine to determine an optimal policy that accomplishes the task. We prove that the algorithm successfully infers the reward machine and asymptotically learns a policy that accomplishes the respective task.</p></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"333 ","pages":"Article 104146"},"PeriodicalIF":14.4,"publicationDate":"2024-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0004370224000821/pdfft?md5=00403f012b025daac195daf945ec2715&pid=1-s2.0-S0004370224000821-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141178018","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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}

引用次数: 0

Credulous acceptance in high-order argumentation frameworks with necessities: An incremental approach 有必然性的高阶论证框架中的可信接受：渐进方法

IF 14.4 2区计算机科学

Artificial Intelligence Pub Date : 2024-05-22 DOI: 10.1016/j.artint.2024.104159

Gianvincenzo Alfano , Andrea Cohen , Sebastian Gottifredi , Sergio Greco , Francesco Parisi , Guillermo R. Simari

{"title":"Credulous acceptance in high-order argumentation frameworks with necessities: An incremental approach","authors":"Gianvincenzo Alfano , Andrea Cohen , Sebastian Gottifredi , Sergio Greco , Francesco Parisi , Guillermo R. Simari","doi":"10.1016/j.artint.2024.104159","DOIUrl":"10.1016/j.artint.2024.104159","url":null,"abstract":"<div><p>Argumentation is an important research area in the field of AI. There is a substantial amount of work on different aspects of Dung's abstract Argumentation Framework (AF). Two relevant aspects considered separately so far are: <em>i</em>) extending the framework to account for recursive attacks and supports, and <span><math><mi>i</mi><mi>i</mi><mo>)</mo></math></span> considering dynamics, <em>i.e.</em>, AFs evolving over time. In this paper, we jointly deal with these two aspects. We focus on High-Order Argumentation Frameworks with Necessities (HOAFNs) which allow for attack and support relations (interpreted as <em>necessity</em>) not only between arguments but also targeting attacks and supports at any level. We propose an approach for the incremental evaluation of the credulous acceptance problem in HOAFNs, by “incrementally” computing an extension (a set of accepted arguments, attacks and supports), if it exists, containing a given goal element in an updated HOAFN. In particular, we are interested in monitoring the credulous acceptance of a given argument, attack or support (goal) in an evolving HOAFN. Thus, our approach assumes to have a HOAFN Δ, a goal <em>ϱ</em> occurring in Δ, an extension <em>E</em> for Δ containing <em>ϱ</em>, and an update <em>u</em> establishing some changes in the original HOAFN, and uses the extension for first checking whether the update is relevant; for relevant updates, an extension of the updated HOAFN containing the goal is computed by translating the problem to the AF domain and leveraging on AF solvers. We provide formal results for our incremental approach and empirically show that it outperforms the evaluation from scratch of the credulous acceptance problem for an updated HOAFN.</p></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"333 ","pages":"Article 104159"},"PeriodicalIF":14.4,"publicationDate":"2024-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141136689","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Optimizing pathfinding for goal legibility and recognition in cooperative partially observable environments 在部分可观测的合作环境中优化寻路，实现目标可读性和识别性

IF 14.4 2区计算机科学

Artificial Intelligence Pub Date : 2024-05-21 DOI: 10.1016/j.artint.2024.104148

Sara Bernardini , Fabio Fagnani , Alexandra Neacsu , Santiago Franco

{"title":"Optimizing pathfinding for goal legibility and recognition in cooperative partially observable environments","authors":"Sara Bernardini , Fabio Fagnani , Alexandra Neacsu , Santiago Franco","doi":"10.1016/j.artint.2024.104148","DOIUrl":"10.1016/j.artint.2024.104148","url":null,"abstract":"<div><p>In this paper, we perform a joint design of goal legibility and recognition in a cooperative, multi-agent pathfinding setting with partial observability. More specifically, we consider a set of identical agents (the actors) that move in an environment only partially observable to an observer in the loop. The actors are tasked with reaching a set of locations that need to be serviced in a timely fashion. The observer monitors the actors' behavior from a distance and needs to identify each actor's destination based on the actor's observable movements. Our approach generates legible paths for the actors; namely, it constructs one path from the origin to each destination so that these paths overlap as little as possible while satisfying budget constraints. It also equips the observer with a goal-recognition mapping between unique sequences of observations and destinations, ensuring that the observer can infer an actor's destination by making the minimum number of observations (legibility delay). Our method substantially extends previous work, which is limited to an observer with full observability, showing that optimizing pathfinding for goal legibility and recognition can be performed via a reformulation into a classical minimum cost flow problem in the partially observable case when the algorithms for the fully observable case are appropriately modified. Our empirical evaluation shows that our techniques are as effective in partially observable settings as in fully observable ones.</p></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"333 ","pages":"Article 104148"},"PeriodicalIF":14.4,"publicationDate":"2024-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0004370224000845/pdfft?md5=66bd75617c41f8c0d650bfa7aefc5bfd&pid=1-s2.0-S0004370224000845-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141136365","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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}

引用次数: 0

Acquiring and modeling abstract commonsense knowledge via conceptualization 通过概念化获取抽象常识并建立模型

IF 14.4 2区计算机科学

Artificial Intelligence Pub Date : 2024-05-17 DOI: 10.1016/j.artint.2024.104149

Mutian He, Tianqing Fang, Weiqi Wang, Yangqiu Song

{"title":"Acquiring and modeling abstract commonsense knowledge via conceptualization","authors":"Mutian He, Tianqing Fang, Weiqi Wang, Yangqiu Song","doi":"10.1016/j.artint.2024.104149","DOIUrl":"10.1016/j.artint.2024.104149","url":null,"abstract":"<div><p>Conceptualization, or viewing entities and situations as instances of abstract concepts in mind and making inferences based on that, is a vital component in human intelligence for commonsense reasoning. Despite recent progress in artificial intelligence to acquire and model commonsense attributed to neural language models and commonsense knowledge graphs (CKGs), conceptualization is yet to be introduced thoroughly, making current approaches ineffective to cover knowledge about countless diverse entities and situations in the real world. To address the problem, we thoroughly study the role of conceptualization in commonsense reasoning, and formulate a framework to replicate human conceptual induction by acquiring abstract knowledge about events regarding abstract concepts, as well as higher-level triples or inferences upon them. We then apply the framework to ATOMIC, a large-scale human-annotated CKG, aided by the taxonomy Probase. We annotate a dataset on the validity of contextualized conceptualizations from ATOMIC on both event and triple levels, develop a series of heuristic rules based on linguistic features, and train a set of neural models to generate and verify abstract knowledge. Based on these components, a pipeline to acquire abstract knowledge is built. A large abstract CKG upon ATOMIC is then induced, ready to be instantiated to infer about unseen entities or situations. Finally, we empirically show the benefits of augmenting CKGs with abstract knowledge in downstream tasks like commonsense inference and zero-shot commonsense QA.</p></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"333 ","pages":"Article 104149"},"PeriodicalIF":14.4,"publicationDate":"2024-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141027260","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Knowledge is power: Open-world knowledge representation learning for knowledge-based visual reasoning 知识就是力量：基于知识的视觉推理的开放世界知识表征学习

IF 14.4 2区计算机科学

Artificial Intelligence Pub Date : 2024-05-13 DOI: 10.1016/j.artint.2024.104147

Wenbo Zheng , Lan Yan , Fei-Yue Wang

{"title":"Knowledge is power: Open-world knowledge representation learning for knowledge-based visual reasoning","authors":"Wenbo Zheng , Lan Yan , Fei-Yue Wang","doi":"10.1016/j.artint.2024.104147","DOIUrl":"10.1016/j.artint.2024.104147","url":null,"abstract":"<div><p>Knowledge-based visual reasoning requires the ability to associate outside knowledge that is not present in a given image for cross-modal visual understanding. Two deficiencies of the existing approaches are that (1) they only employ or construct elementary and <em>explicit</em> but superficial knowledge graphs while lacking complex and <em>implicit</em> but indispensable cross-modal knowledge for visual reasoning, and (2) they also cannot reason new/<em>unseen</em> images or questions in open environments and are often violated in real-world applications. How to represent and leverage tacit multimodal knowledge for open-world visual reasoning scenarios has been less studied. In this paper, we propose a novel open-world knowledge representation learning method to not only construct implicit knowledge representations from the given images and their questions but also enable knowledge transfer from a <em>known</em> given scene to an <em>unknown</em> scene for answer prediction. Extensive experiments conducted on six benchmarks demonstrate the superiority of our approach over other state-of-the-art methods. We apply our approach to other visual reasoning tasks, and the experimental results show that our approach, with its good performance, can support related reasoning applications.</p></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"333 ","pages":"Article 104147"},"PeriodicalIF":14.4,"publicationDate":"2024-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140949791","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Learning spatio-temporal dynamics on mobility networks for adaptation to open-world events 学习移动网络的时空动态，以适应开放世界事件

IF 5.1 2区计算机科学

Artificial Intelligence Pub Date : 2024-05-08 DOI: 10.1016/j.artint.2024.104120

{"title":"Learning spatio-temporal dynamics on mobility networks for adaptation to open-world events","authors":"","doi":"10.1016/j.artint.2024.104120","DOIUrl":"10.1016/j.artint.2024.104120","url":null,"abstract":"<div><p>As a decisive part in the success of Mobility-as-a-Service (MaaS), spatio-temporal dynamics modeling on mobility networks is a challenging task particularly considering scenarios where open-world events drive mobility behavior deviated from the routines. While tremendous progress has been made to model high-level spatio-temporal regularities with deep learning, most, if not all of the existing methods are neither aware of the dynamic interactions among multiple transport modes on mobility networks, nor adaptive to unprecedented volatility brought by potential open-world events. In this paper, we are therefore motivated to improve the canonical spatio-temporal network (ST-Net) from two perspectives: (1) design a heterogeneous mobility information network (HMIN) to explicitly represent intermodality in multimodal mobility; (2) propose a memory-augmented dynamic filter generator (MDFG) to generate sequence-specific parameters in an on-the-fly fashion for various scenarios. The enhanced <u>e</u>vent-<u>a</u>ware <u>s</u>patio-<u>t</u>emporal <u>net</u>work, namely <strong>EAST-Net</strong>, is evaluated on several real-world datasets with a wide variety and coverage of open-world events. Both quantitative and qualitative experimental results verify the superiority of our approach compared with the state-of-the-art baselines. What is more, experiments show generalization ability of EAST-Net to perform zero-shot inference over different open-world events that have not been seen.</p></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"335 ","pages":"Article 104120"},"PeriodicalIF":5.1,"publicationDate":"2024-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141043763","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

A multi-graph representation for event extraction 用于事件提取的多图表示法

IF 14.4 2区计算机科学

Artificial Intelligence Pub Date : 2024-05-03 DOI: 10.1016/j.artint.2024.104144

Hui Huang , Yanping Chen , Chuan Lin , Ruizhang Huang , Qinghua Zheng , Yongbin Qin

{"title":"A multi-graph representation for event extraction","authors":"Hui Huang , Yanping Chen , Chuan Lin , Ruizhang Huang , Qinghua Zheng , Yongbin Qin","doi":"10.1016/j.artint.2024.104144","DOIUrl":"https://doi.org/10.1016/j.artint.2024.104144","url":null,"abstract":"<div><p>Event extraction has a trend in identifying event triggers and arguments in a unified framework, which has the advantage of avoiding the cascading failure in pipeline methods. The main problem is that joint models usually assume a one-to-one relationship between event triggers and arguments. It leads to the argument multiplexing problem, in which an argument mention can serve different roles in an event or shared by different events. To address this problem, we propose a multigraph-based event extraction framework. It allows parallel edges between any nodes, which is effective to represent semantic structures of an event. The framework enables the neural network to map a sentence(s) into a structurized semantic representation, which encodes multi-overlapped events. After evaluated on four public datasets, our method achieves the state-of-the-art performance, outperforming all compared models. Analytical experiments show that the multigraph representation is effective to address the argument multiplexing problem and helpful to advance the discriminability of the neural network for event extraction.</p></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"332 ","pages":"Article 104144"},"PeriodicalIF":14.4,"publicationDate":"2024-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140843426","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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