Efficient and Effective Multi-Modal Queries Through Heterogeneous Network Embedding

Karl Aberer, Chi Thang Duong, Quoc Viet Hung Nguyen, Thành Tâm Nguyên
IEEE COMPUTER SOC, 2022
Journal paper

Abstract

The heterogeneity of today's Web sources requires information retrieval (IR) systems to handle multi-modal queries. Such queries define a user's information needs by different data modalities, such as keywords, hashtags, user profiles, and other media. Recent IR systems answer such a multi-modal query by considering it as a set of separate uni-modal queries. However, depending on the chosen operationalisation, such an approach is inefficient or ineffective. It either requires multiple passes over the data or leads to inaccuracies since the relations between data modalities are neglected in the relevance assessment. To mitigate these challenges, we present an IR system that has been designed to answer genuine multi-modal queries. It relies on a heterogeneous network embedding, so that features from diverse modalities can be incorporated when representing both, a query and the data over which it shall be evaluated. By embedding a query and the data in the same vector space, the relations across modalities are made explicit and exploited for more accurate query evaluation. At the same time, multi-modal queries are answered with a single pass over the data. An experimental evaluation using diverse real-world and synthetic datasets illustrates that our approach returns twice the amount of relevant information compared to baseline techniques, while scaling to large multi-modal databases.

Official source

https://infoscience.epfl.ch/record/297459?ln=en

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Related concepts

Related publications

Mobile service robots are going to play an increasing role in the society of humans. Voice-enabled interaction with service robots becomes very important, if such robots are to be deployed in real-world environments and accepted by the vast majority of potential human users. The research presented in this thesis addresses the problem of speech recognition integration in an interactive voice-enabled interface of a service robot, in particular a tour-guide robot. The task of a tour-guide robot is to engage visitors to mass exhibitions (users) in dialogue providing the services it is designed for (e.g. exhibit presentations) within a limited time. In managing tour-guide dialogues, extracting the user goal (intention) for requesting a particular service at each dialogue state is the key issue. In mass exhibition conditions speech recognition errors are inevitable because of noisy speech and uncooperative users of robots with no prior experience in robotics. They can jeopardize the user goal identification. Wrongly identified user goals can lead to communication failures. Therefore, to reduce the risk of such failures, methods for detecting and compensating for communication failures in human-robot dialogue are needed. During the short-term interaction with visitors, the interpretation of the user goal at each dialogue state can be improved by combining speech recognition in the speech modality with information from other available robot modalities. The methods presented in this thesis exploit probabilistic models for fusing information from speech and auxiliary modalities of the robot for user goal identification and communication failure detection. To compensate for the detected communication failures we investigate multimodal methods for recovery from communication failures. To model the process of modality fusion, taking into account the uncertainties in the information extracted from each input modality during human-robot interaction, we use the probabilistic framework of Bayesian networks. Bayesian networks are graphical models that represent a joint probability function over a set of random variables. They are used to model the dependencies among variables associated with the user goals, modality related events (e.g. the event of user presence that is inferred from the laser scanner modality of the robot), and observed modality features providing evidence in favor of these modality events. Bayesian networks are used to calculate posterior probabilities over the possible user goals at each dialogue state. These probabilities serve as a base in deciding if the user goal is valid, i.e. if it can be mapped into a tour-guide service (e.g. exhibit presentation) or is undefined – signaling a possible communication failure. The Bayesian network can be also used to elicit probabilities over the modality events revealing information about the possible cause for a communication failure. Introducing new user goal aspects (e.g. new modality events and related features) that provide auxiliary information for detecting communication failures makes the design process cumbersome, calling for a systematic approach in the Bayesian network modelling. Generally, introducing new variables for user goal identification in the Bayesian networks can lead to complex and computationally expensive models. In order to make the design process more systematic and modular, we adapt principles from the theory of grounding in human communication. When people communicate, they resolve understanding problems in a collaborative joint effort of providing evidence of common shared knowledge (grounding). We use Bayesian network topologies, tailored to limited computational resources, to model a state-based grounding model fusing information from three different input modalities (laser, video and speech) to infer possible grounding states. These grounding states are associated with modality events showing if the user is present in range for communication, if the user is attending to the interaction, whether the speech modality is reliable, and if the user goal is valid. The state-based grounding model is used to compute probabilities that intermediary grounding states have been reached. This serves as a base for detecting if the the user has reached the final grounding state, or wether a repair dialogue sequence is needed. In the case of a repair dialogue sequence, the tour-guide robot can exploit the multiple available modalities along with speech. For example, if the user has failed to reach the grounding state related to her/his presence in range for communication, the robot can use its move modality to search and attract the attention of the visitors. In the case when speech recognition is detected to be unreliable, the robot can offer the alternative use of the buttons modality in the repair sequence. Given the probability of each grounding state, and the dialogue sequence that can be executed in the next dialogue state, a tour-guide robot has different preferences on the possible dialogue continuation. If the possible dialogue sequences at each dialogue state are defined as actions, the introduced principle of maximum expected utility (MEU) provides an explicit way of action selection, based on the action utility, given the evidence about the user goal at each dialogue state. Decision networks, constructed as graphical models based on Bayesian networks are proposed to perform MEU-based decisions, incorporating the utility of the actions to be chosen at each dialogue state by the tour-guide robot. These action utilities are defined taking into account the tour-guide task requirements. The proposed graphical models for user goal identification and dialogue error handling in human-robot dialogue are evaluated in experiments with multimodal data. These data were collected during the operation of the tour-guide robot RoboX at the Autonomous System Lab of EPFL and at the Swiss National Exhibition in 2002 (Expo.02). The evaluation experiments use component and system level metrics for technical (objective) and user-based (subjective) evaluation. On the component level, the technical evaluation is done by calculating accuracies, as objective measures of the performance of the grounding model, and the resulting performance of the user goal identification in dialogue. The benefit of the proposed error handling framework is demonstrated comparing the accuracy of a baseline interactive system, employing only speech recognition for user goal identification, and a system equipped with multimodal grounding models for error handling.

EPFL2006

Mobility-centric design of collaborative transportation systems

Embedded sensors and actuators are revolutionizing the way we perceive and interact with the physical world. Current research on such Cyber-Physical Systems (CPSs) has focused mostly on distributed sensing and data gathering. The next step is to move from passive information extraction from the physical world towards an active framework where information is retrieved, processed, and acted upon in situ. As an example of such sensor-actuator systems that provide large-scale, distributed coordination, we consider Intelligent Transportation Systems (ITSs), with the goal of increasing travel safety and efficiency. The proliferation of wireless technologies enables different actors (e.g., pedestrians, motorists, traffic operators) to communicate with each other cheaply, efficiently, and securely. By embedding computational intelligence, communication and control into such ITSs, it will be possible to build collaborative transportation applications that help solve, for example, congestion and parking problems. This thesis explores the following question: To what extent is it possible to build distributed ITS systems that rely exclusively on local communication between nodes? The potential benefits of building such systems without infrastructure are numerous, including lower fixed and variable costs, avoiding regulatory hurdles, lower entry barriers for new players, and more control over privacy. On the other hand, self-organized ITSs without infrastructure have to operate under challenging conditions: large scale, high mobility, lack of end-to-end connectivity, ephemeral contacts between wireless nodes, and heterogeneous node capabilities. Although the networking research community has invested a significant effort in designing service abstractions that mimic traditional IP connectivity on top of wireless ad hoc networks, the ITS scenarios considered in this work are too challenging to implement such a service model. The main goal of this thesis is to design communication service models and their underlying protocols that can operate in collaborative transportation applications, and to demonstrate their effectiveness through analysis of traffic data and through realistic simulations. A key point is that the ITS applications we consider can rely on more limited service primitives, because they do not require a general any-to-any delivery service with strict performance guarantees. We first define the collaborative transportation applications of interest. Then we quantify their potential benefits and discuss their functional requirements. Next, we focus on the problem of the collection of large-scale mobility data. We propose a new method for collecting such data and introduce a novel mobility data mining framework, which is necessary to study collective mobility patterns in the context of wireless ad hoc networking. Relying on the analysis of real-life mobility traces, we find that despite the high node mobility, clusters of time-stable connectivity emerge and last at specific locations. Outside such clusters the connectivity between nodes remains sparse. This leads us to the proposal of a new mobility model that captures in an elegant way two phenomena observed in reality, i.e., emergence of stable clusters and network partitioning. This mobility model, called Heterogeneous Random Walk (HRW), appears to be the worst-case mobility model for many mobility-assisted protocols. Moreover, we show that the HRW mobility model predicts the performance of an epidemic dissemination protocol more accurately than other, similarly parsimonious models. Based on the lessons learned from the mobility data analysis, we propose a new abstraction that allows us to capture collective mobility patterns. This abstraction, called a Mobility Map, can be shared globally among mobile nodes and it can be used to improve communication in mobile partitioned networks (MPNs). Notably, we present a new geocasting protocol called GeoMobCast, which uses Mobility Maps to minimize message delay. This protocol is designed to provide the users of the collective transportation applications with the required communication service. Finally, we turn our attention on the real-life implementation of the distributed ITS that leverage short-range wireless communication. To this extent, we present the results of our experimental work with wireless sensor network technologies. We also present the necessary simulation toolbox designed to implement and evaluate collaborative transportation applications.

EPFL2009

High-Dimensional Inference on Dense Graphs with Applications to Coding Theory and Machine Learning

Mohamad Baker Dia

We are living in the era of "Big Data", an era characterized by a voluminous amount of available data. Such amount is mainly due to the continuing advances in the computational capabilities for capturing, storing, transmitting and processing data. However, it is not always the volume of data that matters, but rather the "relevant" information that resides in it. Exactly 70 years ago, Claude Shannon, the father of information theory, was able to quantify the amount of information in a communication scenario based on a probabilistic model of the data. It turns out that Shannon's theory can be adapted to various probability-based information processing fields, ranging from coding theory to machine learning. The computation of some information theoretic quantities, such as the mutual information, can help in setting fundamental limits and devising more efficient algorithms for many inference problems. This thesis deals with two different, yet intimately related, inference problems in the fields of coding theory and machine learning. We use Bayesian probabilistic formulations for both problems, and we analyse them in the asymptotic high-dimensional regime. The goal of our analysis is to assess the algorithmic performance on the first hand and to predict the Bayes-optimal performance on the second hand, using an information theoretic approach. To this end, we employ powerful analytical tools from statistical physics. The first problem is a recent forward-error-correction code called sparse superposition code. We consider the extension of such code to a large class of noisy channels by exploiting the similarity with the compressed sensing paradigm. Moreover, we show the amenability of sparse superposition codes to perform joint distribution matching and channel coding. In the second problem, we study symmetric rank-one matrix factorization, a prominent model in machine learning and statistics with many applications ranging from community detection to sparse principal component analysis. We provide an explicit expression for the normalized mutual information and the minimum mean-square error of this model in the asymptotic limit. This allows us to prove the optimality of a certain iterative algorithm on a large set of parameters. A common feature of the two problems stems from the fact that both of them are represented on dense graphical models. Hence, similar message-passing algorithms and analysis tools can be adopted. Furthermore, spatial coupling, a new technique introduced in the context of low-density parity-check (LDPC) codes, can be applied to both problems. Spatial coupling is used in this thesis as a "construction technique" to boost the algorithmic performance and as a "proof technique" to compute some information theoretic quantities. Moreover, both of our problems retain close connections with spin glass models studied in statistical mechanics of disordered systems. This allows us to use sophisticated techniques developed in statistical physics. In this thesis, we use the potential function predicted by the replica method in order to prove the threshold saturation phenomenon associated with spatially coupled models. Moreover, one of the main contributions of this thesis is proving that the predictions given by the "heuristic" replica method are exact. Hence, our results could be of great interest for the statistical physics community as well, as they help to set a rigorous mathematical foundation of the replica predictions.