There has been substantial work in recent years on grounded language acquisition, in which language and sensor data are used to create a model relating linguistic constructs to the perceivable world. While powerful, this approach is frequently hindered by ambiguities, redundancies, and omissions found in natural language. We describe an unsupervised system that learns language by training visual classifiers, first selecting important terms from object descriptions, then automatically choosing negative examples from a paired corpus of perceptual and linguistic data. We evaluate the effectiveness of each stage as well as the system's performance on the overall learning task.

This paper introduces a novel methodology for 3D template matching that is scalable to higher-dimensional spaces and larger kernel sizes. It uses the Hilbert Maps framework to model raw pointcloud information as a continuous occupancy function, and we derive a closed-form solution to the convolution operation that takes place directly in the Reproducing Kernel Hilbert Space defining these functions. The result is a third function modeling activation values, that can be queried at arbitrary resolutions with logarithmic complexity, and by iteratively searching for high similarity areas we can determine matching candidates. Experimental results show substantial speed gains over standard discrete convolution techniques, such as sliding window and fast Fourier transform, along with a significant decrease in memory requirements, without accuracy loss. This efficiency allows the proposed methodology to be used in areas where discrete convolution is currently infeasible. As a practical example we explore the key problem in robotics of global localization, in which a vehicle must be positioned on a map using only its current sensor information, and provide comparisons with other state-of-the-art techniques in terms of computational speed and accuracy.

Probabilistic topic models are popular unsupervised learning methods, including probabilistic latent semantic indexing (pLSI) and latent Dirichlet allocation (LDA). By now, their training is implemented on general purpose computers (GPCs), which are flexible in programming but energy-consuming. Towards low-energy implementations, this paper investigates their training on an emerging hardware technology called the neuromorphic multi-chip systems (NMSs). NMSs are very effective for a family of algorithms called spiking neural networks (SNNs). We present three SNNs to train topic models.The first SNN is a batch algorithm combining the conventional collapsed Gibbs sampling (CGS) algorithm and an inference SNN to train LDA. The other two SNNs are online algorithms targeting at both energy- and storage-limited environments. The two online algorithms are equivalent with training LDA by using maximum-a-posterior estimation and maximizing the semi-collapsed likelihood, respectively.They use novel, tailored ordinary differential equations for stochastic optimization. We simulate the new algorithms and show that they are comparable with the GPC algorithms, while being suitable for NMS implementation. We also propose an extension to train pLSI and a method to prune the network to obey the limited fan-in of some NMSs.

In the propositional setting, the marginal problem is to find a (maximum-entropy) distribution that has some given marginals. We study this problem in a relational setting and make the following contributions. First, we compare two different notions of relational marginals. Second, we show a duality between the resulting relational marginal problems and the maximum likelihood estimation of the parameters of relational models, which generalizes a well-known duality from the propositional setting. Third, by exploiting the relational marginal formulation, we present a statistically sound method to learn the parameters of relational models that will be applied in settings where the number of constants differs between the training and test data. Furthermore, based on a relational generalization of marginal polytopes, we characterize cases where the standard estimators based on feature's number of true groundings needs to be adjusted and we quantitatively characterize the consequences of these adjustments. Fourth, we prove bounds on expected errors of the estimated parameters, which allows us to lower-bound, among other things, the effective sample size of relational training data.

Weight learning is a challenging problem in Markov Logic Networks (MLNs) due to the large size of the ground propositional probabilistic graphical model that underlies the first-order representation of MLNs. Though more sophisticated weight learning methods that use lifted inference have been proposed, such methods can typically scale up only in the absence of evidence, namely in generative weight learning. In discriminative learning, where the evidence typically destroys symmetries, existing approaches are lacking in scalability. In this paper, we propose a novel, intuitive approach for learning MLNs discriminatively by utilizing approximate symmetries. Specifically, we reduce the size of the training database by clustering approximately symmetric atoms together and selecting a representative atom from each cluster. However, each choice made from the clusters induces a different distribution, increasing the uncertainty in our learned model. To reduce this uncertainty, we learn a finite mixture model by stacking the different distributions, where the parameters of the model are learned using an EM approach. Our results on several benchmarks show that our approach is much more scalable and accurate as compared to existing state-of-the-art MLN learning methods.

Sensor-based activity recognition aims to predict users' activities from multi-dimensional streams of various sensor readings received from ubiquitous sensors. To use machine learning techniques for sensor-based activity recognition, previous approaches focused on composing a feature vector to represent sensor-reading streams received within a period of various lengths. With the constructed feature vectors, e.g., using predefined orders of moments in statistics, and their corresponding labels of activities, standard classification algorithms can be applied to train a predictive model, which will be used to make predictions online. However, we argue that in this way some important information, e.g., statistical information captured by higher-order moments, may be discarded when constructing features. Therefore, in this paper, we propose a new method, denoted by SMMAR, based on learning from distributions for sensor-based activity recognition. Specifically, we consider sensor readings received within a period as a sample, which can be represented by a feature vector of infinite dimensions in a Reproducing Kernel Hilbert Space (RKHS) using kernel embedding techniques. We then train a classifier in the RKHS. To scale-up the proposed method, we further offer an accelerated version by utilizing an explicit feature map instead of using a kernel function. We conduct experiments on four benchmark datasets to verify the effectiveness and scalability of our proposed method.

End-to-end argument mining has enabled the development of new automated essay scoring (AES) systems that use argumentative features (e.g., number of claims, number of support relations) in addition to traditional legacy features (e.g., grammar, discourse structure) when scoring persuasive essays. While prior research has proposed different argumentative features as well as empirically demonstrated their utility for AES, these studies have all had important limitations. In this paper we identify a set of desiderata for evaluating the use of argument mining for AES, introduce an end-to-end argument mining system and associated argumentative feature sets, and present the results of several studies that both satisfy the desiderata and demonstrate the value-added of argument mining for scoring persuasive essays.

Word embedding has been widely used in many natural language processing tasks. In this paper, we focus on learning word embeddings through selective higher-order relationships in sentences to improve the embeddings to be less sensitive to local context and more accurate in capturing semantic compositionality. We present a novel multi-order dependency-based strategy to composite and represent the context under several essential constraints. In order to realize selective learning from the word contexts, we automatically assign the strengths of different dependencies between co-occurred words in the stochastic gradient descent process. We evaluate and analyze our proposed approach using several direct and indirect tasks for word embeddings. Experimental results demonstrate that our embeddings are competitive to or better than state-of-the-art methods and significantly outperform other methods in terms of context stability. The output weights and representations of dependencies obtained in our embedding model conform to most of the linguistic characteristics and are valuable for many downstream tasks.

Named entity disambiguation (NED) is a central problem in information extraction. The goal is to link entities in a knowledge graph (KG) to their mention spans in unstructured text. Each distinct mention span (like John Smith, Jordan or Apache) represents a multi-class classification task. NED can therefore be modeled as a multitask problem with tens of millions of tasks for realistic KGs. We initiate an investigation into neural representations, network architectures, and training protocols for multitask NED. Specifically, we propose a task-sensitive representation learning framework that learns mention dependent representations, followed by a common classifier. Parameter learning in our framework can be decomposed into solving multiple smaller problems involving overlapping groups of tasks. We prove bounds for excess risk, which provide additional insight into the problem of multi-task representation learning. While remaining practical in terms of training memory and time requirements, our approach outperforms recent strong baselines, on four benchmark data sets.

Distant supervised relation extraction is an efficient approach to scale relation extraction to very large corpora, and has been widely used to find novel relational facts from plain text. Recent studies on neural relation extraction have shown great progress on this task via modeling the sentences in low-dimensional spaces, but seldom considered syntax information to model the entities. In this paper, we propose to learn syntax-aware entity embedding for neural relation extraction. First, we encode the context of entities on a dependency tree as sentence-level entity embedding based on tree-GRU. Then, we utilize both intra-sentence and inter-sentence attentions to obtain sentence set-level entity embedding over all sentences containing the focus entity pair. Finally, we combine both sentence embedding and entity embedding for relation classification. We conduct experiments on a widely used real-world dataset and the experimental results show that our model can make full use of all informative instances and achieve state-of-the-art performance of relation extraction.