As tech giants like Google, Facebook, Apple and Microsoft continue to invest in speech technology, the global voice recognition market is projected to reach a value of $133 billion by 2017 (companiesandmarkets.com, 2015). Speech-enabled interactive systems in particular, such as Apple's Siri and Microsoft's Cortana, are starting to show significant economic impact, with the virtual personal assistant (VPA) market estimated to grow from $352 million in 2012 to over $3 billion in 2020 (Grand View Research, 2014). Although such commercial systems allow consumers to use their voice in interacting with their devices and services, the user experience is still limited due to the lack of naturalness of the conversations and limited social intelligence of the VPA. Moreover, the quality of these user interfaces relies on large, carefully crafted rule sets, making development labour-intensive and not scalable to new application domains. With the emergence of the Internet of Things and voice control in the smart home, there is a huge demand for scalable development of natural conversational interfaces across task domains. MaDrIgAL will develop a radically new approach to building interactive spoken language interfaces by exploiting the multi-dimensional nature of natural language conversation: in addition to carrying out the underlying task or activity, participants in a dialogue simultaneously address several other aspects of communication, such as giving and eliciting feedback and adhering to social conventions. In analogy to the singing voices in a madrigal, simultaneous processes for each dimension operate in harmony to produce multifunctional, natural utterances. Consider the two alternative responses S2a and S2b in the following example: U1: Hello, I would like to book a flight to London. S2a: Which date did you have in mind? S2b: Ok, flying to London on what date? Whereas S2a only asks for the next piece of information to book the flight (uni-dimensional), S2b also gives feedback about the arrival city, allowing the user to correct any recognition errors (multi-dimensional). We aim to develop a principled multidimensional modelling and learning framework that covers a wide range of different phenomena, including the implicit confirmation in S2b. This multi-dimensional approach will not only allow us to build systems that support more natural and effective interactions with users, but also enables cost-effective development of such interfaces for a variety of domains by learning transferable conversational skills (e.g., selecting actions in domain independent dimensions). We will therefore demonstrate our approach by building interactive spoken language interfaces for multiple application domains in a home automation scenario, allowing users to interact with for example their Smart TV or heating control system. We will closely collaborate with the industrial partner SemVox to explore this scenario. The project will bring together expertise in statistical machine learning approaches to state-of-the-art spoken dialogue systems and natural language generation, as well as linguistic theories of multi-dimensional dialogue modelling (collaborating in particular with academic partner Prof. Bunt). MaDrIgAL will develop Next Generation Interaction Technologies relevant to Health Technology and Assisted Living, as well as tackle the question of a common user interface to the Internet of Things and Big Data.

In many European countries public opinion is polarized on issues such as immigration, inequality, populism, and trust in institutions. Although for each issue there is an extended literature, there is a pressing need for integration. Are opinions on these issues related and, if so, what is the glue that binds them? Do different groups of people polarize on different issues and/or for different reasons? Our first objective is to determine how identities and threat combine to generate multiple polarized attitudes. First, we use the novel technique of correlational class analysis to identify subpopulations with unique belief systems, consisting of threats, identities, and polarized attitudes. These analyses are followed by experiments that test causal effects of identities and threats, and how these may differ between subpopulations with different belief systems. Our second objective is to compare subpopulations of belief systems across countries and over time. Therefore, cross-country differences in belief systems will be related to variation in the political landscape (e.g., political polarisation), and differences in social structural country characteristics (e.g., inequality and meritocratic beliefs). Longitudinally we will examine the impact of the financial crisis on belief systems. Crucially, identifying subpopulations with different belief systems will help not only in understanding polarisation, but also in identifying solutions, which are expected to differ depending on the belief system. Democratic innovations such as citizen fora have been developed to overcome polarisation. We will test whether using our insights on threats and identity can make such fora more effective.

European cities face complex challenges that demand smart solutions. This project puts urban intermediaries, those people who can bring people and resources together in innovative ways, at the heart of smart urban development and sets out to understand how they create social innovation. We will carry out fieldwork in four European cities (Birmingham, Copenhagen, Glasgow and Amsterdam) where we will develop collaborative working groups, or 'living labs', which will be sources of data as well as sites for learning across projects, fields of practice, cities and countries. In sum, we will advance knowledge of how intermediaries innovate and generate smart urban development, by creating opportunities for collaborative research, dialogue and learning across Europe.

Over the past few months, we have laid the groundwork for the ReproHum project (summarised in the 'pre-project' column in the Work Plan document) with (i) a study of 20 years of human evaluation in NLG which reviewed and labelled 171 papers in detail, (ii) the development of a classification system for NLP evaluations, (iii) a proposal for a shared task for reproducibility of human evaluation in NLG, and (iv) a proposal for a workshop on human evaluation in NLP. We have built an international network of 20 research teams currently working on human evaluation who will actively contribute to this project (see Track Record section), making combined contributions in kind of over £80,000. This pre-project activity has created an advantageous starting position for the proposed work, and means we can 'hit the ground running' with the scientifically interesting core of the work. In this foundational project, our key goals are the development of a methodological framework for testing the reproducibility of human evaluations in NLP, and of a multi-lab paradigm for carrying out such tests in practice, carrying out the first study of this kind in NLP. We will (i) systematically diagnose the extent of the human evaluation reproducibility problem in NLP and survey related current work to address it (WP1); (ii) develop the theoretical and methodological underpinnings for reproducibility testing in NLP (WP2); (iii) test the suitability of the shared-task paradigm (uniformly popular across NLP fields) for reproducibility testing (WP3); (iv) create a design for multi-test reproducibility studies, and run the ReproHum study, an international large-scale multi-lab effort conducting 50+ individual, coordinated reproduction attempts on human evaluations in NLP from the past 10 years (WP4); and (v) nurture and build international consensus regarding how to address the reproducibility crisis, via technical meetings and growing our international network of researchers (WP5).

Urban logistics has become increasingly fragmented due to on-demand and time-sensitive delivery. Urban distribution systems have become multi-tier and multi-modal, and increasingly include multiple deconsolidation, cross-dock, and inventory locations. This implies an increase in the use of urban space, both for storage and movement of goods. While models to support urban planners and companies have advanced substantially, the combination of space and time requirements have received little attention. We develop innovative strategies leveraging advanced analytics to cope with the inherent dynamics of the urban logistics system, including stochastic models designed to support decision makers to best use of existing networks of logistics facilities and delivery modes, and to cope with limited urban space while meeting the increasing and time-sensitive customer expectations. We take a ground-breaking approach to also include the welfare of delivery couriers explicitly into our modelling approach, recognizing the anxiety and stress that human logistics operators face in this challenging environment. Our strategies and models are evaluated based on the urban realities of Bordeaux (France) and Chengdu (China). This allows us to compare logistics practice in two medium-sized cities with various topology and business environment, and with relatively low urban density to that in a metropolis with extremely high density.