Emiel Krahmer

Learn More
This article describes a new approach to the generation of referring expressions. We propose to formalize a scene (consisting of a set of objects with various properties and relations) as a labeled directed graph and describe content selection (which properties to include in a referring expression) as a subgraph construction problem. Cost functions are used(More)
In this paper we describe a method for simplifying sentences using Phrase Based Machine Translation, augmented with a re-ranking heuristic based on dissimilarity, and trained on a monolingual parallel corpus. We compare our system to a word-substitution baseline and two state-of-the-art systems, all trained and tested on paired sentences from the English(More)
Speakers may use pitch accents as pointers to new information, or as signals of a contrast relation between the accented item and a limited set of alternatives. There is no consensus in the literature whether a separately identi able contrastive accent exists. Some studies report that contrastive accents are more emphatic than newness accents and have a di(More)
Given the state of the art of current language and speech technology, errors are unavoidable in present-day spoken dialogue systems. Therefore, one of the main concerns in dialogue design is how to decide whether or not the system has understood the user correctly. In human-human communication, dialogue participants are continuously sending and receiving(More)
We report on an exploratory experimental comparison of two different thinking aloud approaches in a usability test that focussed on navigation problems in a highly non-standard website. One approach is a rigid application of Ericsson and Simon's (1993) procedure, the other is derived from a recent proposal by Boren and Ramey (2000), based on speech(More)
This paper describes two experiments on the role of audiovisual prosody for signalling and detecting meta-cognitive information in question answering. The Wrst study consists of an experiment, in which participants are asked factual questions in a conversational setting, while they are being Wlmed. Statistical analyses bring to light that the speakers’(More)
Sentence fusion is a text-to-text (revision-like) generation task which takes related sentences as input and merges these into a single output sentence. In this paper we describe our ongoing work on developing a sentence fusion module for Dutch. We propose a generalized version of alignment which not only indicates which words and phrases should be aligned(More)
This article offers a survey of computational research on referring expressions generation (REG). It introduces the REG problem and describes early work in this area, discussing what basic assumptions lie behind it, and showing how its remit has widened in recent years. We discuss computational frameworks underlying REG, and demonstrate a recent trend that(More)
This article reports on a comparative analysis of accentuation strategies within Italian and Dutch noun phrases (NPs). Its goal is not only to gain insight into what speakers do, but also into how listeners’ perception and interpretation of incoming speech in different languages is affected by the distribution of accents. To this end, use is made of a(More)
We investigate to what extent automatic learning techniques can be used for shallow interpretation of user utterances in spoken dialogue systems. This task involves dialogue act classification, shallow understanding and problem detection simultaneously. For this purpose we train both a rule-induction and a memory-based learning algorithm on a large set of(More)