Search

The importance of the efforts to bridge the gap between the connectionist and symbolic paradigms of artificial intelligence has been widely recognized. The merging of theory (background knowledge) and data learning (learning from examples) into neural-symbolic systems has indicated that such a learning system is more effective than purely symbolic or purely connectionist systems. Until recently, however, neural-symbolic systems were not able to fully represent, reason, and learn expressive languages other than classical propositional and fragments of first-order logic. In this article, we show that nonclassical logics, in particular propositional temporal logic and combinations of temporal and epistemic (modal) reasoning, can be effectively computed by artificial neural networks. We present the language of a connectionist temporal logic of knowledge (CTLK). We then present a temporal algorithm that translates CTLK theories into ensembles of neural networks and prove that the translation is correct. Finally, we apply CTLK to the muddy children puzzle, which has been widely used as a test-bed for distributed knowledge representation. We provide a complete solution to the puzzle with the use of simple neural networks, capable of reasoning about knowledge evolution in time and of knowledge acquisition through learning.

Objective: Handling time-related concepts is essential in medicine. During diagnosis it can make a substantial difference to know the temporal order in which some symptoms occurred or for how long they lasted. During prognosis the potential evolutions of a disease are conceived as a description of events unfolding in time. In therapy planning the different steps of treatment must be applied in a precise order, with a given frequency and for a certain span of time in order to be effective. This article offers a survey on the use of temporal reasoning for decision support-related tasks in medicine., Material and Methods: Key publications of the area, mainly circumscribed to the latest two decades, are reviewed and classified according to three important stages of patient treatment requiring decision support: diagnosis, prognosis and therapy planning/management. Other complementary publications, like those on time-centered information storage and retrieval, are also considered as they provide valuable support to the above mentioned three stages., Results: Key areas are highlighted and used to organize the latest contributions. The survey of previous research is followed by an analysis of what can still be improved and what is needed to make the next generation of decision support systems for medicine more effective., Conclusions: It can be observed that although the area has been considerably developed, there are still areas where more research is needed to make time-based systems of widespread use in decision support-related areas of medicine. Several suggestions for further exploration are proposed as a result of the survey.

The recognition of high level clinical scenes is fundamental in patient monitoring. In this paper, we propose a technique for recognizing a session, i.e. the clinical process evolution, by comparison against a predetermined set of scenarios, i.e. the possible behaviors for this process. We use temporal constraint networks to represent both scenario and session. Specific operations on networks are then applied to perform the recognition task. An index of temporal proximity is introduced to quantify the degree of matching between two temporal networks in order to select the best scenario fitting a session. We explore the application of our technique, implemented in the Déjà Vu system, to the recognition of typical medical scenarios with both precise and imprecise temporal information.

In most development tools for knowledge-based systems object-property-value-triples are the basic ontological representation. We have extended this approach for temporal reasoning by replacing the values with time-objects. A time-object is a combination of a value with a time-point or a time-interval. By preserving the object-property-value-triples basic artificial intelligence techniques can be applied without modifications in the temporal case. The greater complexity of temporal inferences is compensated by a blackboard control architecture enabling small knowledge-sources. The control of the strategic reasoning is in accordance with the select and test model. A prototype of a knowledge-based advisor for the acute radiation syndrome has been implemented and partially evaluated. Due to the affected proliferative tissues it is a strongly time-oriented medical domain.

We present a brief, nonexhaustive overview of research efforts in designing and developing time-oriented systems in medicine. The growing volume of research on time-oriented systems in medicine can be viewed from either an application point of view, focusing on different generic tasks (e.g. diagnosis) and clinical areas (e.g. cardiology), or from a methodological point of view, distinguishing between different theoretical approaches. In this overview, we focus on highlighting methodological and theoretical choices, and conclude with suggestions for new research directions. Two main research directions can be noted: temporal reasoning, which supports various temporal inference tasks (e.g. temporal abstraction, time-oriented decision support, forecasting, data validation), and temporal data maintenance, which deals with storage and retrieval of data that have heterogeneous temporal dimensions. Efforts common to both research areas include the modeling of time, of temporal entities, and of temporal queries. We suggest that tasks such as abstraction of time-oriented data and the handling of different temporal-granularity levels should provide common ground for collaboration between the two research directions and fruitful areas for future research.

We have added temporal reasoning to the Heart Disease Program (HDP) to take advantage of the temporal constraints inherent in cardiovascular reasoning. Some processes take place over minutes while others take place over months or years and a strictly probabilistic formalism can generate hypotheses that are impossible given the temporal relationships involved. The HDP has temporal constraints on the causal relations specified in the knowledge base and temporal properties on the patient input provided by the user. These are used in two ways. First, they are used to constrain the generation of the pre-computed causal pathways through the model that speed the generation of hypotheses. Second, they are used to generate time intervals for the instantiated nodes in the hypotheses, which are matched and adjusted as nodes are added to each evolving hypothesis. This domain offers a number of challenges for temporal reasoning. Since the nature of diagnostic reasoning is inferring a causal explanation from the evidence, many of the temporal intervals have few constraints and the reasoning has to make maximum use of those that exist. Thus, the HDP uses a temporal interval representation that includes the earliest and latest beginning and ending specified by the constraints. Some of the disease states can be corrected but some of the manifestations may remain. For example, a valve disease such as aortic stenosis produces hypertrophy that remains long after the valve has been replaced. This requires multiple time intervals to account for the existing findings. This paper discusses the issues and solutions that have been developed for temporal reasoning integrated with a pseudo-Bayesian probabilistic network in this challenging domain for diagnosis.

Studying the Brain's Electrical and Magnetic Signals (BEMS) requires the contribution of many area of research that include anatomy, neurophysiology and electromagnetic theory. NEUROLAB is a framework dedicated to the study of brain disorders. Upon completion, it should provide users with an intelligent computational environment that incorporates qualitative and quantitative models of the brain and head, and a model for representing and reasoning about time and space. Spatio-temporal knowledge of a given problem is represented as a constraint network where to each node of the network are attached temporal and spatial variables that must satisfy the constraints defined by the arch labels connecting the nodes. In this paper, we show how temporal reasoning can be combined with spatial descriptions to produce different scenarios of possible seizure spread. These scenarios can provide a priori information for the inverse problem the role of which is to localise the sources of the observed BEMS.

A medical decision-support system (MDSS) employs either explicit or implicit temporal representation and reasoning (TRR). In this paper we first examine the factors that make explicit TRR necessary. We argue that for diagnostic MDSSs in large domains, such as internal medicine, implicit TRR is often sufficient for acceptable diagnostic performance. A necessary prerequisite for implementing implicit TRR is the identification of a set of proper TRR abstractions. We analyze the implicit TRR utilized in QMR, a MDSS operating in the domain of general internal medicine, and describe three classes of TRR abstractions. We discuss our findings in relation to work on temporal reasoning in medical informatics.

Superficial knowledge about drug effects and interactions may provide clinicians with only a limited support for the elaboration of therapy plans. Deeper knowledge of the mechanisms through which drugs produce their effects, together with their temporal constraints, should be modelled to predict the effects and interactions of their joint administration. The present paper describes a method for modelling such deep medical knowledge, together with its causal and temporal reasoning capabilities, and compares it with classical approaches to temporal and causal reasoning, namely in the context of drug treatment applications. This method extends a previous causal functional model by allowing the representation of quantitative knowledge, the explicit representation of time intervals, and a temporal reasoning technique, Simulation by Interval Constraining. The method is illustrated by a number of examples of basic drug metabolic mechanisms; and its future use in the development of decision support systems for complex drug therapy applications is discussed.

Qualitative spatial/temporal reasoning (QSR/QTR) plays a key role in research on human cognition, e.g., as it relates to navigation, as well as in work on robotics and artificial intelligence. Although previous work has mainly focused on various spatial and temporal calculi, more recently representation learning techniques such as embedding have been applied to reasoning and inference tasks such as query answering and knowledge base completion. These subsymbolic and learnable representations are well suited for handling noise and efficiency problems that plagued prior work. However, applying embedding techniques to spatial and temporal reasoning has received little attention to date. In this paper, we explore two research questions: (1) How do embedding-based methods perform empirically compared to traditional reasoning methods on QSR/QTR problems? (2) If the embedding-based methods are better, what causes this superiority? In order to answer these questions, we first propose a hyperbolic embedding model, called HyperQuaternionE, to capture varying properties of relations (such as symmetry and anti-symmetry), to learn inversion relations and relation compositions (i.e., composition tables), and to model hierarchical structures over entities induced by transitive relations. We conduct various experiments on two synthetic datasets to demonstrate the advantages of our proposed embedding-based method against existing embedding models as well as traditional reasoners with respect to entity inference and relation inference. Additionally, our qualitative analysis reveals that our method is able to learn conceptual neighborhoods implicitly. We conclude that the success of our method is attributed to its ability to model composition tables and learn conceptual neighbors, which are among the core building blocks of QSR/QTR. [ABSTRACT FROM AUTHOR]

After a review of situation theory and previous attempts at `computational' situation theory, we present a new programming environment, BABY-SIT, which is based on situation theory. We then demonstrate how problems requiring formal temporal reasoning can be solved in this framework. Specifically, the Yale Shooting Problem, which is commonly regarded as a canonical problem for nonmonotonic temporal reasoning, is implemented in BABY-SIT using Yoav Shoham's causal theories.

Vision and language understanding has emerged as a subject undergoing intense study in Artificial Intelligence. Among many tasks in this line of research, visual question answering (VQA) has been one of the most successful ones, where the goal is to learn a model that understands visual content at region-level details and finds their associations with pairs of questions and answers in the natural language form. Despite the rapid progress in the past few years, most existing work in VQA have focused primarily on images. In this paper, we focus on extending VQA to the video domain and contribute to the literature in three important ways. First, we propose three new tasks designed specifically for video VQA, which require spatio-temporal reasoning from videos to answer questions correctly. Next, we introduce a new large-scale dataset for video VQA named TGIF-QA that extends existing VQA work with our new tasks. Finally, we propose a dual-LSTM based approach with both spatial and temporal attention and show its effectiveness over conventional VQA techniques through empirical evaluations. [ABSTRACT FROM AUTHOR]

Rigorous comparisons of human and machine learning algorithm performance on the same task help to support accurate claims about algorithm success rates and advances understanding of their performance relative to that of human performers. In turn, these comparisons are critical for supporting advances in artificial intelligence. However, the machine learning community has lacked a standardized, consensus framework for performing the evaluations of human performance necessary for comparison. We demonstrate common pitfalls in a designing the human performance evaluation and propose a framework for the evaluation of human performance, illustrating guiding principles for a successful comparison. These principles are first, to design the human evaluation with an understanding of the differences between human and algorithm cognition; second, to match trials between human participants and the algorithm evaluation, and third, to employ best practices for psychology research studies, such as the collection and analysis of supplementary and subjective data and adhering to ethical review protocols. We demonstrate our framework's utility for designing a study to evaluate human performance on a one-shot learning task. Adoption of this common framework may provide a standard approach to evaluate algorithm performance and aid in the reproducibility of comparisons between human and machine learning algorithm performance., (© 2022. The Author(s).)

Conceptual abstraction and analogy-making are key abilities underlying humans' abilities to learn, reason, and robustly adapt their knowledge to new domains. Despite a long history of research on constructing artificial intelligence (AI) systems with these abilities, no current AI system is anywhere close to a capability of forming humanlike abstractions or analogies. This paper reviews the advantages and limitations of several approaches toward this goal, including symbolic methods, deep learning, and probabilistic program induction. The paper concludes with several proposals for designing challenge tasks and evaluation measures in order to make quantifiable and generalizable progress in this area., (© 2021 New York Academy of Sciences.)

We present here a theory of motion from a topological point of view, in a symbolic perspective. Taking space–time histories of objects as primitive entities, we introduce temporal and topological relations on the thus defined space–time to characterize classes of spatial changes. The theory thus accounts for qualitative spatial information, dealing with underspecified, symbolic information when accurate data are not available or unnecessary. We show that these structures give a basis for commonsense spatio–temporal reasoning by presenting a number of significant deductions in the theory. This can serve as a formal basis for languages describing motion events in a qualitative way. [ABSTRACT FROM AUTHOR]

Distributed artificial intelligence (DAI) is suitable for applications where there is no central control. One of these applications with which we are concerned is transportation scheduling. We noticed that all the approaches dedicated to this application use a weak representation of time and a simple reasoning. Furthermore, these approaches ignore the uncertain behavior of agents. What we propose is an approach based on fuzzy temporal characteristic functions (FTCF), which allows a powerful representation of agent company behaviors informing us at each time about the degree that the agent is available. Thanks to this representation, we develop a spatio-temporal reasoning allowing a cooperation inter-and intra-companies to allocate trucks and delegate orders. First, we use an offline scheduling algorithm that takes charge of new transportation tasks only when trucks are at a destination. To increase the performance of the system, we need to introduce the ability to take charge of the new transportation task immediately and to delegate it to a truck while this latter is moving toward a destination. For this purpose, the system needs to address two issues: (1) determining the current location of the truck and its proximity to the departure and arrival of the new transportation task and (2) respecting the temporal constraints. For this purpose, we use a spatio-temporal reasoning allowing us to deal with the first issue using a spatial reasoning and then addressing the second issue using a temporal reasoning. This approach is a first step towards a design of a temporally situated multi-agent system that allows us to take location and the time at which agents are at this location to determine the suitable actions. [ABSTRACT FROM AUTHOR]

Copyright of Praxis Filosófica is the property of Universidad del Valle and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The authors propose a high-level scenario recognition algorithm for video sequence interpretation. The recognition of scenarios is based on a Bayesian networks approach. The model of a scenario contains two main layers. The first one allows events from the observed visual features to be highlighted and the second layer is focused on the temporal reasoning stage. The temporal layer uses specific nodes permitting an event-based approach. These nodes focus on the lifetime of events highlighted from the results of the first layer. The temporal layer then estimates the qualitative and quantitative relations between the different temporal events helpful for the recognition task. The global recognition algorithm is illustrated over real indoor image sequences of an abandoned baggage scenario. [ABSTRACT FROM AUTHOR]

This paper argues for the use of conceptual spaces in qualitative spatial and temporal reasoning. Conceptual spaces provide a natural framework for enriching the purely combinatorial and symbolic calculi such as Allen's calculus with a geometrical or topological structure. Recent work has shown that such enrichments are useful, since they provide simpler ways of characterizing tractable subclasses of the calculi. Hence part of the computational properties can be related to geometrical properties. The paper discusses a family of calculi (including Allen's calculus) for which substantial results have been obtained using this approach. It then examines other instances of calculi where the relationship has not yet been fully investigated and lists the main open questions which arise in this context. [ABSTRACT FROM AUTHOR]

After a review of situation theory and previous attempts at ‘computational’ situation theory, we present a new programming environment, BABY-SIT, which is based on situation theory. We then demonstrate how problems requiring formal temporal reasoning can be solved in this framework. Specifically, the Yale Shooting Problem, which is commonly regarded as a canonical problem for nonmonotonic temporal reasoning, is implemented in BABY-SIT using Yoav Shoham’s causal theories. [ABSTRACT FROM AUTHOR]

Abstract: Representing and reasoning about time dependent information is a key research issue in many areas of computer science and artificial intelligence. One of the best known and widely used formalisms for representing interval-based qualitative temporal information is Allen''s interval algebra (IA). The fundamental reasoning task in IA is to find a scenario that is consistent with the given information. This problem is in general NP-complete. In this paper, we investigate how an interval-based representation, or IA network, can be encoded into a propositional formula of Boolean variables and/or predicates in decidable theories. Our task is to discover whether satisfying such a formula can be more efficient than finding a consistent scenario for the original problem. There are two basic approaches to modelling an IA network: one represents the relations between intervals as variables and the other represents the end-points of each interval as variables. By combining these two approaches with three different Boolean satisfiability (SAT) encoding schemes, we produced six encoding schemes for converting IA to SAT. In addition, we also showed how IA networks can be formulated into satisfiability modulo theories (SMT) formulae based on the quantifier-free integer difference logic (QF-IDL). These encodings were empirically studied using randomly generated IA problems of sizes ranging from 20 to 100 nodes. A general conclusion we draw from these experimental results is that encoding IA into SAT produces better results than existing approaches. More specifically, we show that the new point-based 1-D support SAT encoding of IA produces consistently better results than the other alternatives considered. In comparison with the six different SAT encodings, the SMT encoding came fourth after the point-based and interval-based 1-D support schemes and the point-based direct scheme. Further, we observe that the phase transition region maps directly from the IA encoding to each SAT or SMT encoding, but, surprisingly, the location of the hard region varies according to the encoding scheme. Our results also show a fixed performance ranking order over the various encoding schemes. [Copyright &y& Elsevier]

In many application areas, including planning, workflow, guideline and protocol management, the description of the domain involves composite and/or periodic events, mutually related by temporal constraints on the execution order. Such events represent ‘classes’, since they can be instantiated to specific executions of the plan, guideline etc., and each execution must ‘respect’ the temporal constraints imposed on the corresponding classes. The main goal of our work is to propose an approach dealing with the above-mentioned temporal phenomena. To achieve such an objective, the authors propose a tractable domain-independent temporal reasoner. This enhances the generality of our approach, which provides a domain-independent module that can be integrated with other software tools to solve temporal problems in specific domains. From the methodological point of view, the authors first devise a representation formalism coping with the aforesaid phenomena, and then they describe temporal constraint propagation algorithms to deal with constraint inheritance and to perform temporal consistency checking. The representation formalism has been designed carefully, to obtain algorithms that are both complete and tractable. Finally, the paper also shows experimental results, including an application of the authors’ approach to clinical guidelines, evaluating their impact on future applications and research activities. [ABSTRACT FROM AUTHOR]

Time is a central factor in patient monitoring. Introduction of domain-dependent knowledge is essential to ensure efficiency of time managers, especially when embedded into systems that interact with the real world. We present a realistic temporal reasoning model based on two basic cognitive mechanisms: aggregation of similar observed situations and forgetting of non-relevant information. We describe in detail how we represented the proposed model and how, by refinement of domain-independent temporal entities and inferences, we added domain specific knowledge to manage a clinical therapy. The model allows clinical observations to be incrementally interpreted as they are acquired by an intelligent system, mainly reactive in its reasoning, for the management of patients receiving respiratory support. [ABSTRACT FROM AUTHOR]

Background: Clinical practice guidelines (CPGs) are assuming a major role in the medical area, to grant the quality of medical assistance, supporting physicians with evidence-based information of interventions in the treatment of single pathologies. The treatment of patients affected by multiple diseases (comorbid patients) is one of the main challenges for the modern healthcare. It requires the development of new methodologies, supporting physicians in the treatment of interactions between CPGs. Several approaches have started to face such a challenging problem. However, they suffer from a substantial limitation: they do not take into account the temporal dimension. Indeed, practically speaking, interactions occur in time. For instance, the effects of two actions taken from different guidelines may potentially conflict, but practical conflicts happen only if the times of execution of such actions are such that their effects overlap in time., Objectives: We aim at devising a methodology to detect and analyse interactions between CPGs that considers the temporal dimension., Methods: In this paper, we first extend our previous ontological model to deal with the fact that actions, goals, effects and interactions occur in time, and to model both qualitative and quantitative temporal constraints between them. Then, we identify different application scenarios, and, for each of them, we propose different types of facilities for user physicians, useful to support the temporal detection of interactions., Results: We provide a modular approach in which different Artificial Intelligence temporal reasoning techniques, based on temporal constraint propagation, are widely exploited to provide users with such facilities. We applied our methodology to two cases of comorbidities, using simplified versions of CPGs., Conclusion: We propose an innovative approach to the detection and analysis of interactions between CPGs considering different sources of temporal information (CPGs, ontological knowledge and execution logs), which is the first one in the literature that takes into account the temporal issues, and accounts for different application scenarios., (Copyright © 2017 Elsevier B.V. All rights reserved.)

For visual information processing, the derivation of meaningful low-level spatio-temporal information is challenging. In line with human visualisation and perception in spatial problem-solving, we believe explicit representations hold promise for efficient low-level abstractions. An approach for mapping spatial objects and relations, exploring diagrams' representation power for problem visualisation, is presented. Combined, qualitative spatio-temporal reasoning and diagrammatic reasoning directly influence information visualisation and abstraction over the physical substrate of a problem. The framework preserves objects' low-level spatio-temporal information over time, facilitating the interpretation of unique relationships. A 78% average activity recognition accuracy on the CAVIAR and Mind's Eye datasets demonstrates the effectiveness of the suggested abstraction approach. [ABSTRACT FROM AUTHOR]

This article presents information on papers presented in a symposium on the foundations and applications of spatio-temporal reasoning. It was said that significant progress has been made in the area of spatial and temporal reasoning. The progress is made primarily in inventing new domains of space and time and in studying complexity issues in reasoning over them. The interest in the area of spatial and temporal reasoning is still growing, especially within the artificial intelligence community. Dealing with time and space is not restricted to artificial intelligence. Geographic information systems, tracking systems, mobile networks, distributed systems, cooperating autonomous agents, distributed databases, planning, robot motion, and other complex systems challenge the capabilities of existing knowledge representation methods and reasoning techniques. Tony Cohn of the University of Leeds started the symposium with an invited tutorial on qualitative spatio-temporal calculi that gave all the participants the necessary background for discussions. Jayant Sharma gave an application-oriented perspective in his invited talk on spatio-temporal reasoning for location-based services. In his invited tutorial on relation algebras, Ivo Düntsch presented the theoretical perspective. The last invited presentation was by Thomas Barkowsky who gave an overview of the SFB/TR8, a huge German research project on Spatial Cognition, which shows that major grant agencies are realizing the importance of the field and are willing to invest large amounts of money for research in spatiotemporal reasoning.

Objectives: Temporal abstraction (TA) of clinical data aims to abstract and interpret clinical data into meaningful higher-level interval concepts. Abstracted concepts are used for diagnostic, prediction and therapy planning purposes. On the other hand, temporal Bayesian networks (TBNs) are temporal extensions of the known probabilistic graphical models, Bayesian networks. TBNs can represent temporal relationships between events and their state changes, or the evolution of a process, through time. This paper offers a survey on techniques/methods from these two areas that were used independently in many clinical domains (e.g. diabetes, hepatitis, cancer) for various clinical tasks (e.g. diagnosis, prognosis). A main objective of this survey, in addition to presenting the key aspects of TA and TBNs, is to point out important benefits from a potential integration of TA and TBNs in medical domains and tasks. The motivation for integrating these two areas is their complementary function: TA provides clinicians with high level views of data while TBNs serve as a knowledge representation and reasoning tool under uncertainty, which is inherent in all clinical tasks., Methods: Key publications from these two areas of relevance to clinical systems, mainly circumscribed to the latest two decades, are reviewed and classified. TA techniques are compared on the basis of: (a) knowledge acquisition and representation for deriving TA concepts and (b) methodology for deriving basic and complex temporal abstractions. TBNs are compared on the basis of: (a) representation of time, (b) knowledge representation and acquisition, (c) inference methods and the computational demands of the network, and (d) their applications in medicine., Results: The survey performs an extensive comparative analysis to illustrate the separate merits and limitations of various TA and TBN techniques used in clinical systems with the purpose of anticipating potential gains through an integration of the two techniques, thus leading to a unified methodology for clinical systems. The surveyed contributions are evaluated using frameworks of respective key features. In addition, for the evaluation of TBN methods, a unifying clinical domain (diabetes) is used., Conclusion: The main conclusion transpiring from this review is that techniques/methods from these two areas, that so far are being largely used independently of each other in clinical domains, could be effectively integrated in the context of medical decision-support systems. The anticipated key benefits of the perceived integration are: (a) during problem solving, the reasoning can be directed at different levels of temporal and/or conceptual abstractions since the nodes of the TBNs can be complex entities, temporally and structurally and (b) during model building, knowledge generated in the form of basic and/or complex abstractions, can be deployed in a TBN., (Copyright © 2014 Elsevier B.V. All rights reserved.)

Objective: An analysis of the timing of events is critical for a deeper understanding of the course of events within a patient record. The 2012 i2b2 NLP challenge focused on the extraction of temporal relationships between concepts within textual hospital discharge summaries., Materials and Methods: The team from the National Research Council Canada (NRC) submitted three system runs to the second track of the challenge: typifying the time-relationship between pre-annotated entities. The NRC system was designed around four specialist modules containing statistical machine learning classifiers. Each specialist targeted distinct sets of relationships: local relationships, 'sectime'-type relationships, non-local overlap-type relationships, and non-local causal relationships., Results: The best NRC submission achieved a precision of 0.7499, a recall of 0.6431, and an F1 score of 0.6924, resulting in a statistical tie for first place. Post hoc improvements led to a precision of 0.7537, a recall of 0.6455, and an F1 score of 0.6954, giving the highest scores reported on this task to date., Discussion and Conclusions: Methods for general relation extraction extended well to temporal relations, and gave top-ranked state-of-the-art results. Careful ordering of predictions within result sets proved critical to this success.

Background: The Sixth Informatics for Integrating Biology and the Bedside (i2b2) Natural Language Processing Challenge for Clinical Records focused on the temporal relations in clinical narratives. The organizers provided the research community with a corpus of discharge summaries annotated with temporal information, to be used for the development and evaluation of temporal reasoning systems. 18 teams from around the world participated in the challenge. During the workshop, participating teams presented comprehensive reviews and analysis of their systems, and outlined future research directions suggested by the challenge contributions., Methods: The challenge evaluated systems on the information extraction tasks that targeted: (1) clinically significant events, including both clinical concepts such as problems, tests, treatments, and clinical departments, and events relevant to the patient's clinical timeline, such as admissions, transfers between departments, etc; (2) temporal expressions, referring to the dates, times, durations, or frequencies phrases in the clinical text. The values of the extracted temporal expressions had to be normalized to an ISO specification standard; and (3) temporal relations, between the clinical events and temporal expressions. Participants determined pairs of events and temporal expressions that exhibited a temporal relation, and identified the temporal relation between them., Results: For event detection, statistical machine learning (ML) methods consistently showed superior performance. While ML and rule based methods seemed to detect temporal expressions equally well, the best systems overwhelmingly adopted a rule based approach for value normalization. For temporal relation classification, the systems using hybrid approaches that combined ML and heuristics based methods produced the best results.

Ensuring artificial intelligence behaves in such a way that is aligned with human values is commonly referred to as the alignment challenge. Prior work has shown that rational agents, behaving in such a way that maximizes a utility function, will inevitably behave in such a way that is not aligned with human values, especially as their level of intelligence goes up. Prior work has also shown that there is no "one true utility function"; solutions must include a more holistic approach to alignment. This paper describes apprehensive agents: agents that are architected in such a way that their effective utility function is an aggregation of a partial utility function (built by designers, to be maximized) and an expectation of negative feedback on given states (reasoned about, to be minimized). Agents are also capable of performing a temporal reasoning process that approximates designers' intentions in function of environment evolution (a necessary feature for severe mis-alignment to occur). We show that an apprehensive agent, behaving rationally, leverages this internal approximation of designers' intentions to predict negative feedback, and, as a consequence, behaves in such a way that maximizes alignment, without actually receiving any external feedback. We evaluate this strategy on simulated environments that expose mis-alignment opportunities: we show that apprehensive agents are indeed better aligned than their base counterparts and, in contrast with extant techniques, chances of alignment actually improve as agent intelligence grows. [ABSTRACT FROM AUTHOR]

We apply the Fuzzy Temporal Constraint System we have developed to the case of SARS (Severe Acute Respiratory Syndrome). The idea is to characterize the temporal evolution of the symptoms of this ill-known disease by modelling patients’ data in a Fuzzy Temporal Constraint Network. We discuss how the system is able to manage both fuzzy qualitative and metric constraints allowing to represent in a flexible manner the symptoms of different patients. In this way it is possible to deduce characteristic periods of an ill-known disease such as SARS was. A new user interface is included into the architecture of the System. [ABSTRACT FROM AUTHOR]

A major difficulty that occurs in the construction of large production rule-based expert systems is maintaining the correctness, consistency, and completeness of the knowledge base. A method of transforming the production rules into a numerical petri nets (NPNs) model is proposed. These NPNs are high level nets that are necessary to effectively model production rules. The net model is then analysed by using a computer- aided tool to perform reachability analysis. An algorithm is given to generate the reachability set of the nets. This allows the verification of the correctness, consistency, and completeness of the knowledge base. Examples showing the use of this approach are given. [ABSTRACT FROM AUTHOR]

In this paper we advocate the use of multi-dimensional modal logics as a framework for knowledge representation and, in particular, for representing spatio-temporal information. We construct a two-dimensional logic capable of describing topological relationships that change over time. This logic, called PSTL (Propositional Spatio-Temporal Logic) is the Cartesian product of the well-known temporal logic PTL and the modal logic S4u, which is the Lewis system S4 augmented with the universal modality. Although it is an open problem whether the full PSTL is decidable, we show that it contains decidable fragments into which various temporal extensions (both point-based and interval based) of the spatial logic RCC-8 can be embedded. We consider known decidability and complexity results that are relevant to computation with multi-dimensional formalisms and discuss possible directions for further research. [ABSTRACT FROM AUTHOR]

Representing and managing temporal knowledge, in the form of temporal constraints, is a crucial task in many areas, including knowledge representation, planning, and scheduling. The current literature in the area is moving from the treatment of “crisp” temporal constraints to fuzzy or probabilistic constraints, to account for preferences and\or uncertainty. Given a set of temporal constraints, the evaluation of the tightest implied constraints is a fundamental task, which is essential also to provide reliable query-answering facilities. However, while such tasks have been widely addressed for “crisp” temporal constraints, they have not attracted enough attention in the “non-crisp” context yet. We overcome such a limitation, by (i) extending quantitative temporal constraints to cope with preferences, (ii) defining a temporal reasoning algorithm which evaluates the tightest temporal constraints, and (iii) providing suitable query-answering facilities based on it. [ABSTRACT FROM PUBLISHER]

The article provides information on the Association for the Advancement of Artificial Intelligence (AAAI-2007) workshop on spatial and temporal reasoning in the U.S. The objective of the workshop is to bring together related communities of researchers with an interest in the study of representing and reasoning about space or time. The workshop has aimed of gaining fundamental understanding on three causes of current situation including fundamental, methodological, and strategic. Accordingly, the workshop is intended both as forum for discussion, exchange of points of view, and assessment of results and methods and as a source of promotion of the newest advances in the area.

An important contribution of AI to Robotics is the model-centred approach, whereby competent robot behaviour stems from automated reasoning in models of the world which can be changed to suit different environments, physical capabilities and tasks. However models need to capture diverse (and often application-dependent) aspects of the robot’s environment and capabilities. They must also have good computational properties, as robots need to reason while they act in response to perceived context. In this article, we investigate the use of a meta-CSP-based technique to interleave reasoning in diverse knowledge types. We reify the approach through a robotic waiter case study, for which a particular selection of spatial, temporal, resource and action KR formalisms is made. Using this case study, we discuss general principles pertaining to the selection of appropriate KR formalisms and jointly reasoning about them. The resulting integration is evaluated both formally and experimentally on real and simulated robotic platforms. [ABSTRACT FROM PUBLISHER]

Knowledge graph (KG) is a key component of artificial intelligence. In recent years, many large-scale knowledge graphs have been produced and put into practical applications. At present, researchers have proposed many methods to reason facts that do not exist in knowledge graphs using the existing information. However, most traditional reasoning methods lack interpretability, and cannot get the reasoning paths. Therefore, the multi-hop path reasoning method of knowledge graph has gradually become a hot spot. This method finds the next relations through the reinforcement learning agent, gets the whole path, and scores the path. Although these multi-hop path reasoning methods make the reasoning method interpretable, these multi-hop path reasoning methods focus on the choice of relations, ignoring the importance of entities in the path reasoning process. Moreover, with the development of the Temporal Knowledge Graph (TKG), traditional multi-hop path reasoning methods cannot effectively process time information. To solve these problems, a multi-hop path reasoning method of temporal knowledge graph based on multi-agent reinforcement learning is proposed, which is named MA-TPath. MA-TPath uses two agents to perform relation selection and entity selection iteratively. Meanwhile, considering the diversity of temporal reasoning paths, we propose a new type of reward function. In MA-TPath, two agents employ the Long Short-Term Memory Networks (LSTM) to capture current results from the environment and output the corresponding action vectors to the environment through activation functions. Experimentally, MA-TPath outperforms all existing models in 4 out of 4 indicators on the YAGO dataset, 3 out of 4 indicators on the GDETL-5 dataset and the ICEWS-250 dataset, and 1 out of 4 indicators on the ICEWS05–15 dataset. Analysis of the temporal reasoning path indicates that MA-TPath not only surpasses other state-of-the-art reasoning methods over four public temporal knowledge graph datasets but provides rationality for results. ● Proposing a multi-agent reinforcement learning model in TKG. ● Proposing a new reward function, considering entity, path, accuracy and diversity. ● Evaluating our approach to demonstrate its superiority in experiments. [ABSTRACT FROM AUTHOR]

In this work we address the problem of representing and reasoning with temporal knowledge in a very general and flexible manner. To this aim we propose a model of integration of quantitative and qualitative temporal information affected by vagueness and uncertainty. We extend our fuzzy qualitative temporal framework IAfuz integrating the treatment of fuzzy quantitative constraints modeled as trapezoidal distributions. To do this, we extend the treatment of fuzzy temporal constraints considered in the literature and we generalize in a fuzzy direction the classical hybrid approach of temporal constraints integration proposed by Meiri. To show the full expressiveness of the new system, we apply it to represent the fuzzy temporal knowledge in a typical scheduling example. [ABSTRACT FROM AUTHOR]

Video Question Answering (VideoQA) emerges as a prominent trend in the domain of Artificial Intelligence, Computer Vision, and Natural Language Processing. It involves developing systems capable of understanding, analyzing, and responding to questions about the content of videos. The Proposed survey presents an in-depth overview of the current landscape of Question Answering, shedding light on the challenges, methodologies, datasets, and innovative approaches in the domain. The key components of the Video Question Answering (VideoQA) framework include video feature extraction, question processing, reasoning, and response generation. It underscores the importance of datasets in shaping VideoQA research and the diversity of question types, from factual inquiries to spatial and temporal reasoning. The survey highlights the ongoing research directions and future prospects for VideoQA. Finally, the proposed survey gives a road map for future explorations at the intersection of multiple disciplines, emphasizing the ultimate objective of pushing the boundaries of knowledge and innovation. • A clear and informative overview, particularly valuable for beginners to acquire a deeper comprehension of Video Question Answering. • Approaches used in each phase of VideoQA like Video Featurization, Question Featurization, Joint Embedding, and Answer Generation. • A unique perspective on the analysis of a wide range of datasets. • Further furnishes the performance metrics employed to assess the outcomes of VideoQA systems. [ABSTRACT FROM AUTHOR]

Extracting high-order abstract patterns from complex high-dimensional data forms the foundation of human cognitive abilities. Abstract visual reasoning involves identifying abstract patterns embedded within composite images, considered a core competency of machine intelligence. Traditional neuro-symbolic methods often infer unknown objects through data fitting, without fully exploring the abstract patterns within composite images and the sequential sensitivity of visual sequences. This paper constructs a relation model with object-centric inductive biases, learning end-to-end multi-granular rule embeddings at different levels. Through a gating fusion module, the model incrementally integrates explicit representations of objects and abstract relationships. The model incorporates a relational bottleneck method from information theory, separating the input perceptual information from the embeddings of abstract representations, thereby restricting and differentiating feature processing to encourage relational comparisons and induce the extraction of abstract patterns. Furthermore, this paper bridges algebraic operations and machine reasoning through the relational bottleneck method, extracting common patterns of multi-visual objects by identifying invariant sequences within the relational bottleneck matrix. Experimental results on the I-RAVEN dataset demonstrate a total accuracy of 96.8%, surpassing state-of-the-art baseline methods and exceeding human performance at 84.4%. [ABSTRACT FROM AUTHOR]

In recent years, advancements in the interaction and collaboration between humans and have garnered significant attention. Social intelligence plays a crucial role in facilitating natural interactions and seamless communication between humans and Artificial Intelligence (AI). To assess AI's ability to understand human interactions and the components necessary for such comprehension, datasets like Social-IQ have been developed. However, these datasets often rely on a simplistic question-and-answer format and lack justifications for the provided answers. Furthermore, existing methods typically produce direct answers by selecting from predefined choices without generating intermediate outputs, which hampers interpretability and reliability. To address these limitations, we conducted a comprehensive evaluation of AI methods on a video-based Question Answering (QA) benchmark focused on human interactions, leveraging additional annotations related to human responses. Our analysis highlights significant differences between human and AI response patterns and underscores critical shortcomings in current benchmarks. We anticipate that these findings will guide the creation of more advanced datasets and represent an important step toward achieving natural communication between humans and AI. [ABSTRACT FROM AUTHOR]

It is useful for machines to know whether text information remains valid or not for various applications including text comprehension, story understanding, temporal information retrieval, and user state tracking on microblogs as well as via chatbot conversations. This kind of inference is still difficult for current models, including also large language models, as it requires temporal commonsense knowledge and reasoning. We approach in this paper the task of Temporal Validity Reassessment, inspired by traditional natural language reasoning to determine the updates of the temporal validity of text content. The task requires judgment whether actions expressed in a sentence are still ongoing or rather completed, hence, whether the sentence still remains valid or has become obsolete, given the presence of context in the form of a supplementary content such as a follow-up sentence. We first construct our own dataset for this task and train several machine learning models. Then we propose an effective method for learning information from an external knowledge base that gives information regarding temporal commonsense knowledge. Using our prepared dataset, we introduce a machine learning model that incorporates the information from the knowledge base and demonstrate that incorporating external knowledge generally improves the results. We also experiment with different embedding types to represent temporal commonsense knowledge as well as with data augmentation methods to increase the size of our dataset. [ABSTRACT FROM AUTHOR]

Discusses an approach that extends temporal databases and artificial intelligence temporal reasoning techniques. Integration of artificial intelligence temporal reasoning techniques; Extension of relational model to consider qualitative and quantitative temporal constraints both in data expressiveness and query expressiveness.