Search

Collaborative robots can improve ergonomics on factory floors while allowing a higher level of flexibility in production. The evolution of robotics and cyber-physical systems in size and functionality has enabled new applications which were never foreseen in traditional industrial robots. However, the current human-robot collaboration (HRC) technologies are limited in reliability and safety, which are vital in risk-critical scenarios. Certainly, confusion about European safety regulations has led to situations where collaborative robots operate behind security barriers, thus negating their advantages while reducing overall application productivity. Despite recent advances, developing a safe collaborative robotic system for performing complex industrial or daily tasks remains a challenge. Multiple influential factors in HRC make it difficult to define a clear classification to understand the depth of collaboration between humans and robots. In this article, we review the state of the art in reliable collaborative robotic work cells and propose a reference model to combine influential factors such as robot autonomy, collaboration, and safety modes to redefine HRC categorization.

Applying deep learning models to MRI scans of acute stroke patients to extract features that are indicative of short-term outcome could assist a clinician’s treatment decisions. Deep learning models are usually accurate but are not easily interpretable. Here, we trained a convolutional neural network on ADC maps from hyperacute ischaemic stroke patients for prediction of short-term functional outcome and used an interpretability technique to highlight regions in the ADC maps that were most important in the prediction of a bad outcome. Although highly accurate, the model’s predictions were not based on aspects of the ADC maps related to stroke pathophysiology.

It is often the case with new technologies that it is very hard to predict their long-term impacts and as a result, although new technology may be beneficial in the short term, it can still cause problems in the longer term. This is what happened with oil by-products in different areas: the use of plastic as a disposable material did not take into account the hundreds of years necessary for its decomposition and its related long-term environmental damage. Data is said to be the new oil. The message to be conveyed is associated with its intrinsic value. But as in the case of real oil, we should take care to ensure that its use does not create harm in the future. We know from recent history that data can be used in harmful ways, but data also has enormous positive potential when applied to the service of communities. In this article, we highlight the opportunities, problems and best practice of using data.

This is a resource description paper that describes the creation and properties of a set of pseudo-corpora generated artificially from a random walk over the English WordNet taxonomy. Our WordNet taxonomic random walk implementation allows the exploration of different random walk hyperparameters and the generation of a variety of different pseudo-corpora. We find that different combinations of the walk’s hyperparameters result in varying statistical properties of the generated pseudo-corpora. We have published a total of 81 pseudo-corpora that we have used in our previous research, but have not exhausted all possible combinations of hyperparameters, which is why we have also published a codebase that allows the generation of additional WordNet taxonomic pseudo-corpora as needed. Ultimately, such pseudo-corpora can be used to train taxonomic word embeddings, as a way of transferring taxonomic knowledge into a word embedding space.

We present an approach to design the grid searches for hyper-parameter optimization for recurrent neural architectures. The basis for this approach is the use of mutual information to analyze long distance dependencies (LDDs) within a dataset. We also report a set of experiments that demonstrate how using this approach, we obtain state-of-the-art results for DilatedRNNs across a range of benchmark datasets.

Brain vessel status is a promising biomarker for better prevention and treatment in cerebrovascular disease. However, classic rule-based vessel segmentation algorithms need to be hand-crafted and are insufficiently validated. A specialized deep learning method—the U-net—is a promising alternative. Using labeled data from 66 patients with cerebrovascular disease, the U-net framework was optimized and evaluated with three metrics: Dice coefficient, 95% Hausdorff distance (95HD) and average Hausdorff distance (AVD). The model performance was compared with the traditional segmentation method of graph-cuts. Training and reconstruction was performed using 2D patches. A full and a reduced architecture with less parameters were trained. We performed both quantitative and qualitative analyses. The U-net models yielded high performance for both the full and the reduced architecture: A Dice value of ~0.88, a 95HD of ~47 voxels and an AVD of ~0.4 voxels. The visual analysis revealed excellent performance in large vessels and sufficient performance in small vessels. Pathologies like cortical laminar necrosis and a rete mirabile led to limited segmentation performance in few patients. The U-net outperfomed the traditional graph-cuts method (Dice ~0.76, 95HD ~59, AVD ~1.97). Our work highly encourages the development of clinically applicable segmentation tools based on deep learning. Future works should focus on improved segmentation of small vessels and methodologies to deal with specific pathologies

Creating word embeddings that reflect semantic relationships encoded in lexical knowledge resources is an open challenge. One approach is to use a random walk over a knowledge graph to generate a pseudo-corpus and use this corpus to train embeddings. However, the effect of the shape of the knowledge graph on the generated pseudo-corpora, and on the resulting word embeddings, has not been studied. To explore this, we use English WordNet, constrained to the taxonomic (tree-like) portion of the graph, as a case study. We investigate the properties of the generated pseudo-corpora, and their impact on the resulting embeddings. We find that the distributions in the psuedo-corpora exhibit properties found in natural corpora, such as Zipf’s and Heaps’ law, and also ob- serve that the proportion of rare words in a pseudo-corpus affects the performance of its embeddings on word similarity.

Dialogue State Tracking is arguably one of the most challenging tasks among dialogue processing problems due to the uncertainties of language and complexity of dialogue contexts. We argue that this problem is made more challenging by variable dependencies in the dialogue states that must be accounted for in processing. In this paper we give details on our motivation for this argument through statistical tests on a number of dialogue datasets. We also propose a machine learning-based approach called energy-based learning that tackles variable dependencies while performing prediction on the dialogue state tracking tasks.

Incrementality is a fundamental feature of language in real world use. To this point, however, the vast majority of work in automated dialogue processing has focused on language as turn based. In this paper we explore the challenge of incremental dialogue state tracking through the development and analysis of a multi-task approach to incremental dialogue state tracking. We present the design of our incremental dialogue state tracker in detail and provide evaluation against the well known Dialogue State Tracking Challenge 2 (DSTC2) dataset. In addition to a standard evaluation of the tracker, we also provide an analysis of the Incrementality phenomenon in our model’s performance by analyzing how early our models can produce correct predictions and how stable those predictions are. We find that the Multi-Task Learning-based model achieves state-of-the-art results for incremental processing.

Natural language processing (NLP) can be done using either top-down (theory driven) and bottom-up (data driven) approaches, which we call mechanistic and phenomenological respectively. The approaches are frequently considered to stand in opposition to each other. Examining some recent approaches in deep learning we argue that deep neural networks incorporate both perspectives and, furthermore, that leveraging this aspect of deep learning may help in solving complex problems within language technology, such as modelling language and perception in the domain of spatial cognition.

This paper examines to what degree current deep learning architectures for image caption generation capture spatial lan- guage. On the basis of the evaluation of examples of generated captions from the literature we argue that systems capture what objects are in the image data but not where these objects are located: the cap- tions generated by these systems are the output of a language model conditioned on the output of an object detector that cannot capture fine-grained location information. Although language models provide useful knowledge for image captions, we argue that deep learning image captioning architectures should also model geometric rela- tions between objects.

Dialogue State Tracking is an important task in dialogue management as it provides a mechanism to monitor dialogue contributions. In this paper we introduce an Incremental Joint Model as a new approach to the task. Our tracker is capable of incrementally tracking Dialogue States. We base our model and analysis on the datasets provided in the Second Dialogue State Tracking Challenge (DSTC2). Our early stage evaluations are based on comparisons of our tracker with both the baseline model provide by the DSTC2 and also LecTrack: a state-of-the-art incremental LSTM-based tracker. The main finding of our experiments is that moving from an utterance based to incremental word based tracker results in better performance for our RNN based joint task models.

In this paper we argue that since the beginning of the natural language processing or computational linguistics there has been a strong connection between logic and machine learning. First of all, there is something logical about language or linguistic about logic. Secondly, we argue that rather than distinguishing between logic and machine learning, a more useful distinction is between top-down approaches and data-driven approaches. Examining some recent approaches in deep learning we argue that they incorporate both properties and this is the reason for their very successful adoption to solve several problems within language technology.

This paper presents an interactive visualisation tool that encodes the scope chain, and information related to the scope chain, within source code. The main goal of the tool is to support programmers when dealing with issues related to scope and to provide answers to questions such as to which scope does a specific variable or function belong to and can I access a specific variable from the scope I am currently located in. The design guidelines followed during the implementation of the tool, as well as the design rationale behind the main features of the tool are described. Finally, the results of a pilot user experience evaluation study are presented where an interesting observation was that the tool seemed to support programmers in verifying and correcting their assumptions when asked questions about specific scoping issues within a source code document.

This paper presents a short introduction to neural networks and how they are used for machine translation and concludes with some discussion on the current research challenges being addressed by neural machine translation (NMT) research. The primary goal of this paper is to give a no-tears introduction to NMT to readers that do not have a computer science or mathematical background. The secondary goal is to provide the reader with a deep enough understanding of NMT that they can appreciate the strengths of weaknesses of the technology. The paper starts with a brief introduction to standard feed-forward neural networks (what they are, how they work, and how they are trained), this is followed by an introduction to word-embeddings (vector representations of words) and then we introduce recurrent neural networks. Once these fundamentals have been introduced we then focus in on the components of a standard neural-machine translation architecture, namely: encoder networks, decoder language models, and the encoder-decoder architecture.

The Folk Music Analysis Workshop brings together computational music analysis and ethnomusicology. Both symbolic and audio representations of music are considered, with a broad range of scientific approaches being applied (signal processing, graph theory, deep learning). The workshop features a range of interesting talks from international researchers in areas such as Indian classical music, Iranian singing, Ottoman-Turkish Makam music scores, Flamenco singing, Irish traditional music, Georgian traditional music and Dutch folk songs. Invited guest speakers were Anja Volk, Utrecht University and Peter Browne, Technological University Dublin.

This paper presents a study which evaluates the use of a tree visualisation (icicle tree) to encode the hierarchical structure of source code. The tree visualisation was combined with a source code editor in order to function as a compact overview to facilitate the process of comprehending the global structure of a source code document. Results from our study show that pro- viding an overview visualisation led to an increase in accuracy and a decrease in completion time when participants performed counting tasks. However, in locating tasks, the presence of the visualisation led to a decrease in participants’ performance.

We performed an experiment in which human participants interacted through a natural language dialogue interface with a simulated robot to fulfil a series of object manipulation tasks. We introduced errors into the robot’s perception, and observed the resulting problems in the dialogues and their resolutions. We then introduced different methods for the user to request information about the robot’s understanding of the environment. In this work, we describe the effects that the robot’s perceptual errors and the information request options available to the participant had on the reformulation of the referring expressions the participants used when resolving a unsuccessful reference.

In a situated dialogue, misunderstandings may arise if the participants perceive or interpret the environment in different ways. In human-computer dialogue this may be due the sensor errors. We present an experiment system and a series of experiments in which we investigate this problem.

To apply machine learning techniques to the production and interpretation of natural language, we need large amounts of annotated language data. Manual annotation, however, is an expensive and time consuming process since it involves human annotators looking at the data and explicitly adding information that is implicitly contained in the data, based on their judgment. This work presents an approach to automatically annotating referring expressions in situated dialogues by exploiting the interpretation of language by the participants in the dia- logue. We associate instructions concerning objects in the environment with automatically detected events involving these objects and predict the referents of referring expressions in the instructions on the basis of the objects aected by the events. We judge the reliability of these pre- dictions based on the temporal and textual distance between instruction and event. We apply our approach to an annotated corpus and evalu- ate the results against human annotation. The evaluation shows that the approach can be used to accurately annotate a large proportion of the utterances in the corpus dialogues and highlight those utterances for which human annotation is required, thus reducing the amount of human annotation required.

Localisation and navigation are still of the most important issues in mobile robotics. In certain indoor application scenarios Radio frequency identification (RFID) based absolute localisation has been found to be especially successful in supporting navigation. In this paper we examine the feasibility of an RFID and compass based approach to robot localisation and navigation for indoor environments that are dominated by corridors. We present a proof of concept system and show how it can be used to localized within and navigate through an environment.

Localisation and navigation are still two of the most important issues in mobile robotics. In certain indoor application scenarios RFID (radio frequency identification)-based absolute localisation has been found to be especially successful in supporting navigation. In this paper we evaluate the feasibility of an RFID and compass based approach to robot localisation and navigation for indoor environments that are dominated by corridors. We describe our system and evaluate its performance in a small, but full-scale, test environment.

This research outlines an Intelligent Virtual Agent (IVA) interface, where multiple users will be able to interact with 3D avatars. This will take place in a distributed multi-modal environ- ment where the LOK8 Avatar System (AS) will need to locate it’s users from a crowd, using face tracking and novel 3D animation techniques.

Mixed-reality virtual agents are an attractive solution to the problems associated with human-robot interaction, allowing all the expressiveness of virtual characters to be married with the advantages of a physical artifact which exists in a shared environment with the user. However, common approaches to achieving this restrict the virtual characters appearing on top of, or encompassing the robot. This paper describes the Stepping Off the Stage system in which mixed-reality agents are allowed to step off the robot stage and move to other parts of the environment, offering compelling new interaction possibilities.

Engineering education deals primarily with calculating quantitative performance of engineering objects, such as machines, circuits or dams, and with designing variations of these objects. However when engineering graduates enter the workforce they must be able to do a great deal more than solve the technical problems taught in engineering school [1]. More specifically they will need to deal with a great range of problems some of which are not technical engineering problems at all. Examples of such problems include working as part of a larger group, project management, negotiation, component sourcing and an awareness of the multi-disciplinary nature of engineering. Such real-world engineering problems force graduate engineers to draw on their professional and personal resourcefulness, adapt to on-the-job pressure, cope with people problems and broaden their knowledge base. Increased competition and high labour costs put pressure on engineering graduates to contribute to companies as soon as they enter the workplace and reduces the time available to graduates to develop these skills on-the-job. To help students develop real-world engineering skills as part of their engineering education the Mechanical Engineering Department in Technological University Dublin (DIT) three years ago introduced Problem Based Learning (PBL). This paper describes a PBL module for Third Year Mechanical Engineering students at DIT designed to help students refine their soft skills in addition to a deeper understanding of their technical skills. This approach, developed by Kelleher, gives students the opportunity to develop a range of experiences which will prepare them to contribute to their employer on entry to the company.

This papers desibes a set of systems developed at DIT for the Referring Expression Generation challenage at INLG 2008.In Proceedings of the 5th International Natural Language Generation Conference (INLG-08)

Negation is commonly seen in clinical documents [Chapman et al., 2001a] ”In clinical reports the presence of a term does not necessarily indicate the presence of the clinical condition represented by that term. In fact, many of the most frequently described findings and diseases in discharge summaries, radiology reports, history and physical exams, and other transcribed reports are denied in the patient” [Chapman et al., 2001b, page. 301].

This section describes the two systems developed at DIT for the attribute selection track of the REG 2008 challenge. Both of theses systems use an incremental greedy search to generate descriptions, similar to the incremental algorithm described in (Dale and Reiter, 1995). The output of these incremental algorithms are, to a large extent, determined by the order in which the algorithm tests the target object’s attributes for inclusion in the description. Indeed, the major difference between the two systems described in this section is the mechanism used to order the attributes for inclusion.

This paper describes the approach of the DIT AIGroup to the i2b2 Obesity Challenge to build a system to diagnose obesity and related co-morbidities from narrative, unstructured patient records. Based on experimental results a system was developed which used knowledge-light text classification using decision trees, and negation labelling.

The DIT system uses an incremental greedy search to generate descriptions, similar to the incremental algorithm described in (Dale and Reiter, 1995). The selection of the next attribute to be tested for inclusion in the description is ordered by the absolute frequency of each attribute in the training corpus. Attributes are selected in descending order of frequency (i.e. the attribute that occurred most frequently in the training corpus is selected first). Where two or more attributes have the same frequency of occurrence the first attribute found with that frequency is selected. The type attribute is always included in the description. Other attributes are included in the description if they exclude at least 1 distractor from the set of distractors that fulfil the description generated prior that attribute’s selection.The algorithm terminates when a distinguishing description has been generated (i.e., all the distractors have been excluded) or when all the target’s attributes have been tested for inclusion in the description.

This volume contains the papers presented at the Fourth ACL-SIGSEM Workshop on Prepositions. This workshop is endorsed by the ACL Special Interest Group on Semantics (ACL-SIGSEM), and is hosted in conjunction with ACL 2007, taking place on 28th June, 2007 in Prague, the Czech Republic.

The DIT system uses an incremental greedy search to generate descriptions, (similar to the incremental algorithm described in (Dale and Reiter, 1995) ) incremental algorithm). The selection of the next attribute to be tested for inclusion in the description is ordered by the absolute frequency of each attribute in the training corpus. Attributes are selected in descending order of frequency (i.e. the attribute that occurred most frequently in the training corpus is selected first).

DIT’s nascent speech corpus will allow a body of spoken material to be searched for features of informal native speech via a normalised transcription. Once located, the original sound files can be played at normal speed or slowed down in order to better study the recorded speech. The DIT speech corpus treats speed of delivery as a key element in producing the elisions, assimilation, reductions and co-articulations characteristic of native-to-native dialogues. Lack of training in dealing with this spoken register can lead to lack of preparation for the world of real speech and even to a degree of social exclusion. It is also envisaged that non-native speech will be included in the corpus so that comparisons can be drawn between native speech and that of various nativised productions of the same items. The database will therefore be capable of being queried on a multi-factorial basis depending on user needs. The optimal segmentation of the normalised transcript is, however, far from clear, and some of the difficulties will be touched on by this presentation. While the tone unit, as proposed by David Brazil, for example, is attractive as a base unit for displaying the concordanced speech corpus, it nevertheless raises problems when there is a discrepancy between semantic segmentation and actual phonetic delivery. The rationale for the currently adopted minimal unit will be explained and members of the audience will be invited to offer feedback on any requirements their own use of corpora would place on the database.

The paper presents a computational model for a context-dependent analysis of a physical environment in terms of spatial proximity. The model provides a basis for grounding linguistic analyses of spatial expressions in visual perception. The model uses potential fields to model spatial proximity. It has been implemented, and when combined with a handcrafted grammar, is used to enable a conversational robot to carry out a situated dialogue with a human. The key concept in our approach is defining the region that is proximal to a landmark based on the spatial configuration of other objects in the scene. The model extends existing approaches to proximity by including object salience (visual, discourse) and interference effects between multiple objects that could act as landmarks. Theoretically, the model can help motivate the choice between topological and projective prepositions, and provides a basis for defining regions with vague spatial extent.

This research examined the practical effects of cooling the intake air, on the combustion characteristics of a modern motor vehicle operating under simulated road conditions as well as its subsequent impact on the environment. The cooling effect was achieved by taking a typical air conditioning rig as fitted to a modern motor vehicle and incorporating it into the induction system of the car. The test vehicle used was a 1993 Renault Safrane 2.0Vi standard passenger car that was modified as part of the research to facilitate the extraction of the required test information. A series of tests were conducted using ambient temperature air and cold air delivered by the air conditioning rig. The results obtained were consistent and conformed to general automotive beliefs regarding power, fuel consumption and emissions.