Search

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.

Corporate smart city initiatives are just one example of the contemporary culture of surveillance. They rely on extensive information gathering systems and Big Data analysis topredict citizen behaviour and optimise city services. In this paper we argue that many smart city and social media technologies result in a paradox whereby digital inclusion for the purposes of service provision also results in marginalisation and disempowerment of citizens. Drawing upon insights garnered from a digital inclusion workshop conducted in the Galapagos islands, we propose that critically and creatively unpacking the computational techniques embedded in data services is needed as a first step if we are to reimagine neganthropic, sustainable and empowering data services for inhabitants in diverse localities. We propose a therapeutic inspired by the concept of ‘common ground’ from communication theory. Common ground presupposes a symmetry of purpose, shared values and accessible participation processes. When common ground is deployed in the smart city context it prompts us to reimagine data services as an ongoing dialogue between peers, to rethink citizen participation in terms of capabilities and empowerment, and to focus on clear lines ofaccountability and equality of citizen outcomes.

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

An urgent limitation in current Image Captioning models is their tendency to produce generic captions that avoid the interesting detail which makes each image unique. To address this limitation, we propose an approach that enforces a stronger alignment between image regions and specific segments of text. The model architecture is composed of a visual region proposer, a region-order planner and a region-guided caption generator. The region-guided caption generator incorporates a novel information gate which allows visual and textual input of different frequencies and dimensionalities in a Recurrent Neural Network.

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.

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 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.

An emerging trend in music information retrieval (MIR) is the use of supervised machine learning to train automatic music transcription models. A prerequisite of adopting a machine learning methodology is the availability of annotated corpora. However, different genres of music have different characteristics and modelling these characteristics is an important part of creating state of the art MIR systems. Consequently, although some music corpora are available the use of these corpora is tied to the specific music genre, instrument type and recording context the corpus covers. This paper introduces the first corpus of annotations of audio recordings of Irish traditional dance music that covers multiple instrument types and both solo studio and live session recordings. We first discuss the considerations that motivated our design choices in developing the corpus. We then benchmark a number of automatic music transcription algorithms against the corpus. The underlying dataset for this research is available here at Github or here in Arrow .

This paper makes three contributions to the discussion on the applicability of Type Theory with Records (TTR) to embodied dialogue agents. First, it highlights the problem of type assignment or judgements in practical implementations which is resource intensive. Second, it presents a judgement control mechanism, which consists of grouping of types into clusters or states by their thematic relations and selection of types following two mechanisms inspired by the Load Theory of selective attention and cognitive control (Lavie et al., 2004), that addresses this problem. Third, it presents a computational framework, based on Bayesian inference, that offers a basis for future practical experimentation on the feasibility of the proposed approach.

This position paper set out the argument that an interesting avenue of exploration and study of universals and variation in spatial reference is to address this topic in termsa of the universals in human perception and attention and to explore how these universals impact on spatial reference across cultures and languages.

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.

In this paper we examine how people negotiate, interpret and repair the frame of reference (FoR) in online text based dialogues discussing spatial scenes in Swedish. We describe work-in-progress in which participants are given different perspectives of the same scene and asked to locate several objects that are only shown on one of their pictures. This task requires participants to coordinate on FoR in order to identify the missing objects. This study has implications for situated dialogue systems.

We evaluate a substitution based technique for improving Statistical Machine Translation performance on idiomatic multiword expressions. The method operates by performing substitution on the original idiom with its literal meaning before translation, with a second substitution step replacing literal meanings with idioms following translation. We detail our approach, outline our implementation and provide an evaluation of the method for the language pair English/Brazilian-Portuguese. Our results show improvements in translation accuracy on sentences containing either morphosyntactically constrained or unconstrained idioms. We discuss the consequences of our results and outline potential extensions to this process.

Human-computer interactions can be greatly enhanced by the use of 3D avatars, representing both human users and computer systems in 3D virtual spaces. This allows the human user to interface with the computer system in a natural and intuitive human-to-human dialog (human face-to-face conversation). Hence, continuing to blur the boundaries between the real and virtual worlds. This proposed avatar system will go a step further and will use a camera to track the user’s head and eye movements during the dialog. This information will help to build rapport between the user and computer system by registering the user’s emotional state and level of interest. The system will adjust the dialog according to this information paying special attention to the user’s feedback. For example, one obvious benefit for head and eye tracking will be to allow the avatar to make and keep realistic eye contact with the user, but there is lots of room to expand on these techniques in this research.

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.