Although there has been much work in recent years on data-driven natural language generation, little attention has been paid to the fine-grained interactions that arise during microplanning between aggregation, surface realization, and sentence segmentation. In this article, we propose a hybrid symbolic/statistical approach to jointly model the constraints regulating these interactions. Our app...

An exact approach is developed to determine the optimum machining conditions and tool allocation decisions simultaneously to minimize the total production cost on a CNC turning machine. There are multiple machining operations and we consider a set of alternative cutting tool types for each operation. The existing tool management approaches at the system level fail to relate the tooling issues t...

Virtual conversational agents are supposed to combine speech with nonverbal modalities for intelligible and believeable utterances. However, the automatic synthesis of coverbal gestures still struggles with several problems like naturalness in procedurally generated animations, flexibility in pre-defined movements, and synchronization with speech. In this paper, we focus on generating complex m...

Commonly, the output of a referring expression generation system is written text which is, typically, presented to a human user as a one-shot expression. Consequently, the majority of existing REG systems interact with users in a very rigid and strictly turnbased fashion: only after the system has fully completed and delivered the result of the REG process, the user is able to read it and react...

GIVE-2.5 evaluates eight natural language generation (NLG) systems that guide human users through solving a task in a virtual environment. The data is collected via the Internet, and to date, 536 interactions of subjects with one of the NLG systems have been recorded. The systems are compared using both task performance measures and subjective ratings by human users.

A lot of attractive applications in addition to manipulation of session related signaling involve specific processing at media level such as playing media, prompting and collecting media from the user, mixing media streams etc. One of the ways of provisioning applications in managed all IP-based multimedia networks, is based on Open Service Access (OSA) service platform. The paper investigates ...

WYSIWYM (‘What you see is what you meant’) is a user-interface technique which uses natural language generation (NLG) technology to provide feedback for user interactions. To date, the technology has been applied in a number of demonstrator applications, using customised, nonportable implementations. In this demonstration, we introduce a WYSIWYM library package, designed to be used as a modular...

In this paper, we present the D-TUNA corpus, which is the first semantically annotated corpus of referring expressions in Dutch. Its primary function is to evaluate and improve the performance of REG algorithms. Such algorithms are computational models that automatically generate referring expressions by computing how a specific target can be identified to an addressee by distinguishing it from...

Interest in multi-touch interaction with large and small displays surfaces has seen a recent explosion. We describe key moments in " multi-touch's " latest history and rank " multi-touch " in Gartner's five-phase hype cycle. We also (re)highlight the issues that designers have to take into account when designing multi-touch applications on multi-touch sensitive surfaces to address the ensuing p...