We evaluate the statistical dependency parser, Malt, on a new dataset of sentences taken from tweets. We use a version of Malt which is trained on gold standard phrase structure Wall Street Journal (WSJ) trees converted to Stanford labelled dependencies. We observe a drastic drop in performance moving from our in-domain WSJ test set to the new Twitter dataset, much of which has to do with the propagation of part-of-speech tagging errors. Retraining Malt on dependency trees produced by a state-of-the-art phrase structure parser, which has itself been self-trained on Twitter material, results in a significant improvement. We analyse this improvement by examining in detail the effect of the retraining on individual dependency types.

This paper describes a program of research that aims to develop and test healthcare robots for elder care. We describe the aims of the project, the robots developed, and studies we have performed in HRI in elder care. We highlight research design issues that have become apparent in the retirement home setting when testing robots. These issues are relevant to robotics researchers wishing to evaluate the effects of robotic care on older people’s quality of life.

Attacker-defender Stackelberg games have become a popular game-theoretic approach for security with deployments for LAX Police, the FAMS and the TSA. Unfortunately, most of the existing solution approaches do not model two key uncertainties of the real-world: there may be noise in the defender’s execution of the suggested mixed strategy and/or the observations made by an attacker can be noisy. In this paper, we analyze a framework to model these uncertainties, and demonstrate that previous strategies perform poorly in such uncertain settings. We also analyze RECON, a novel algorithm that computes strategies for the defender that are robust to such uncertainties, and explore heuristics that further improve RECON’s efficiency.

Ontologies are not only becoming a widespread formalism to create the knowledge base of current intelligent and semantic systems, but they are also suitable for modeling context information in ubiquitous applications, which require expressive representation and reasoning languages. In this paper, we discuss different approaches for ontological context management, as well as a proposal to represent and exploit significance-based relations with standard and fuzzy ontologies.

Context Management technology is not novel itself, and ICT companies are already looking at this area and spending effort for a long time trying to find a technically feasible solution, appealing marketing usage and solve all the possible issues with its privacy and security concerns. However, after many years of technology scouting and academic scrutiny within this still innovating area, there is no unique best practice or reference standardization solving all the technological difficulties within this field. The context information available in the real world from many potential sources should be handled in a near real-time way, efficiently processed by many devices and be interoperable among different actors dealing with the context. Therefore not only a comprehensive context management framework shall be in the place but also efficient context representation formalism should be employed in order to represent the context data suitably for an autonomous Machine-to-Machine processing, with all the data maintained within that representation and with all the mechanisms or artifacts needed for a secure and privacy safeguarding sensitive data handling. This all compose a set of requirements to be respected in the context information data representation, which are listed and solved by the solution described within with paper.

This paper reports on the linguistic analysis of a tag set of nearly 50,000 tags collected as part of the steve.museum project. The tags describe images of objects in museum collections. We present our results on morphological, part of speech and semantic analysis. We demonstrate that deeper tag processing provides valuable information for organizing and categorizing social tags. This promises to improve access to museum objects by leveraging the characteristics of tags and the relationships between them rather than treating them as individual items. The paper shows the value of using deep computational linguistic techniques in interdisciplinary projects on tagging over images of objects in museums and libraries. We compare our data and analysis to Flickr and other image tagging projects.

Using these custom tools requires have been busily converting material from paper and microfilm training and a skilled workforce. We show in this paper that into digital domain. Newspapers, books, journals and some parts of that process can be distributed to a pool of even individual letters are finding themselves inside large unskilled volunteers with good results.

Being able to detect and recognize human activities is important for making personal assistant robots useful in performing assistive tasks. The challenge is to develop a system that is low-cost, reliable in unstructured home settings, and also straightforward to use. In this paper, we use a RGBD sensor (Microsoft Kinect) as the input sensor, and present learning algorithms to infer the activities. Our algorithm is based on a hierarchical maximum entropy Markov model (MEMM). It considers a person's activity as composed of a set of sub-activities, and infers the two-layered graph structure using a dynamic programming approach. We test our algorithm on detecting and recognizing twelve different activities performed by four people in different environments, such as a kitchen, a living room, an office, etc., and achieve an average performance of 84.3% when the person was seen before in the training set (and 64.2% when the person was not seen before).

Continual learning is the unending process of learning new things on top of what has already been learned (Ring, 1994).Temporal Transition Hierarchies (TTHs) were developed to allow prediction of Markov-k sequences in a way that was consistent with the needs of a continual-learning agent (Ring, 1993).However, the algorithm could not learn arbitrary temporal contingencies.This paper describes Recurrent Transition Hierarchies (RTH), a learning method that combines several properties desirable for agents that must learn as they go.In particular, it learns online and incrementally, autonomously discovering new features as learning progresses.It requires no reset or episodes.It has a simple learning rule with update complexity linear in the number of parameters.

The motor system organization shows some interesting parallels with the language organization. Here we draw the possible communalities between Action and Language, basing our claims on neurophysiological, neuroanatomical and neuroimaging data. Furthermore, we speculate that the motor system may have furnished the basic computational capabilities for the emergence of both semantics and syntax.