ENLG

The paper discusses quality of service evaluation which emphasises the user's experience in the evaluation of system functionality and efficiency. For NLG systems, an important quality feature is communicatively adequate language generation, which ...

Generation of Referring Expressions is a thriving subfield of Natural Language Generation which has traditionally focused on the task of selecting a set of attributes that unambiguously identify a given referent. In this paper, we address the ...

We present a log-linear model that is used for ranking the string realisations produced for given corpus f-structures by a reversible broad-coverage LFG for German and compare its results with the ones achieved by the application of a language model (LM)...

In this paper we present a view of natural language generation in which the control structure of the generator is clearly separated from the content decisions made during generation, allowing us to explore and compare different control strategies in a ...

We investigate two methods for enhancing variation in the output of a stochastic surface realiser: choosing from among the highest-scoring realisation candidates instead of taking the single highest-scoring result (ε-best sampling), and penalising the ...

We present a method for quickly spotting overgeneration suspects (i.e., likely cause of overgeneration) in hand-coded grammars. The method is applied to a medium size Tree Adjoining Grammar (TAG) for French and is shown to help reduce the number of ...

Despite being the focus of intensive research, evaluation of algorithms that generate referring expressions is still in its infancy. We describe a corpus-based evaluation methodology, applied to a number of classic algorithms in this area. The ...

Politeness is an integral part of human language variation, e.g. consider the difference in the pragmatic effect of realizing the same communicative goal with either "Get me a glass of water mate!" or "I wonder if I could possibly have some water please?...

The potential of sentence generators as engines in Intelligent Computer-Assisted Language Learning and teaching (ICALL) software has hardly been explored. We sketch the prototype of COMPASS, a system that supports integrated writing and grammar ...

Central to the vision of the Semantic Grid is the adoption of metadata and ontologies to describe resources, to promote and enhance collaboration (De Roure et al., 2005). This raises the question of how such metadata comes into existence. Ideally the ...

This paper describes a model of the choice of modal verbs and modal particles. The choice mechanism does not require a modality-specific input as, e.g., a modal logical formula. Instead semantic (modal force) and pragmatic constraints (speech act ...

The issue of sentence ordering is an important one for natural language tasks such as multi-document summarization, yet there has not been a quantitative exploration of the range of acceptable sentence orderings for short texts. We present results of a ...

In this paper we introduce a method for generating interactive documents which exploits the visual features of hypertext to represent discourse structure. We explore the consistent and principled use of graphics and animation to support navigation and ...

Existing generation systems use verbs almost exclusively to describe actions/events or to ascribe properties. In doing so, they achieve a direct concrete style of the kind often recommended in style manuals. However in many genres, including academic ...

I present an architecture for data-to-text systems, that is NLG systems which produce texts from non-linguistic input data; this essentially extends the architecture of Reiter and Dale (2000) to systems whose input is raw data instead of AI knowledge ...

This paper introduces our domain independent approach to "free generation" from single RDF triples without using any domain dependent knowledge. Our approach is developed based on our argument that RDF representations carry rich linguistic information, ...

We present the Narrator, an NLG component used for the generation of narratives in a digital story-telling system. We describe how the Narrator works and show some examples of generated stories.

Almost all existing referring expression generation algorithms aim to find one best referring expression for a given intended referent. However, human-produced data demonstrates that, for any given entity, many perfectly acceptable referring expressions ...

We present an empirical approach to adaptively selecting a tutoring system's remediation strategy based on an annotated corpus of human-human tutorial dialogues. We are interested in the remediation selection problem, that of generating the best ...

This paper discusses an implemented dialogue system which generates the meanings of utterances by taking into account: the surface mood of the user's last utterance; the meanings of all the user's utterances from the current discourse; the system's ...

This paper reports on work in progress on extending the entity-based approach on measuring coherence (Barzilay & Lapata, 2005; Lapata & Barzilay, 2005) from coreference to semantic relatedness. We use a corpus of manually annotated German newspaper text ...

We introduce NaturalOWL, an open-source multilingual natural language generator that produces descriptions of instances and classes, starting from a linguistically annotated ontology. The generator is heavily based on ideas from ILEX and M-PIRO, but it ...

This paper discusses the generation of cryptic crossword clues: a task that involves generating texts that have both a surface reading, based on a natural language interpretation of the words, and a hidden meaning in which the strings that form the text ...

We describe a new application for NLG technology: the generation of indicative, abstractive summaries of multi-party meetings. Based on the freely available AMI corpus of 100 hours of recorded meetings, we are developing a summarizer that uses the rich ...

We assess the use of hedge phrases in "affective" NLG texts. A simple experiment suggests non-native speakers prefer texts that contain hedge phrases, but native speakers prefer texts that do not contain hedge phrases.

An existing taxonomy of Dutch cue phrases, designed for use in story generation, was validated by analysing cue phrase usage in a corpus of classical fairy tales. The analysis led to some adaptations of the original taxonomy.

Geo-referenced data which are often communicated via maps are inaccessible to the visually impaired population. We summarise existing approaches to improving accessibility of geo-referenced data and present the Atlas.txt project which aims to produce ...

Medical information is notoriously difficult to convey to patients because the content is complex, emotionally sensitive, and hard to explain without recourse to technical terms. We describe a pilot system for communicating the contents of electronic ...