In this article we discuss several metrics of coherence defined using centering theory and investigate the usefulness of such metrics for information ordering in automatic text generation. We estimate empirically which is the most promising metric and how useful this metric is using a general methodology applied on several corpora. Our main result is that the simplest metric (which relies exclusively on NOCB transitions) sets a robust baseline that cannot be outperformed by other metrics which make use of additional centering-based features. This baseline can be used for the development of both text-to-text and concept-to-text generation systems.

BACKGROUND: Despite increasing interest in applying Natural Language Processing (NLP) to biomedical text, whether this technology can facilitate tasks such as database curation remains unclear. RESULTS: PaperBrowser is the first NLP-powered interface that was developed under a user-centered approach to improve the way in which FlyBase curators navigate an article. In this paper, we first discuss how observing curators at work informed the design and evaluation of PaperBrowser. Then, we present how we appraise PaperBrowser's navigational functionalities in a user-based study using a text highlighting task and evaluation criteria of Human-Computer Interaction. Our results show that PaperBrowser reduces the amount of interactions between two highlighting events and therefore improves navigational efficiency by about 58% compared to the navigational mechanism that was previously available to the curators. Moreover, PaperBrowser is shown to provide curators with enhanced navigational utility by over 74% irrespective of the different ways in which they highlight text in the article. CONCLUSION: We show that state-of-the-art performance in certain NLP tasks such as Named Entity Recognition and Anaphora Resolution can be combined with the navigational functionalities of PaperBrowser to support curation quite successfully.

Text mining is defined by Hearst (1999) as the automatic discovery of new, previously unknown information from unstructured textual data.This is often seen as comprising three major tasks: information retrieval (gathering relevant documents), information extraction (extracting information of interest from these documents), and data mining (discovering new associations among the extracted pieces of information).Most researchers in the natural language processing (NLP) community are familiar with work on information extraction and its subtasks such as noun phrase chunking, named entity recognition, and anaphora resolution, typically applied to newswire articles.The explosive growth of biomedical literature has prompted increasing interest in applying such techniques to biomedical text in order to address the information overload faced by domain experts.This is reflected by the proliferation of articles reviewing this work (Reviews 2006), which typically appear in bioinformatics journals and target experts in biosciences as their primary audience.Text Mining for Biology and Biomedicine provides an overview of the fundamental approaches to biomedical NLP in more depth than is typically offered in a review article.The book consists of an introductory chapter written by the editors and nine chapters that each discuss a different sub-area of biomedical NLP.Each chapter is authored by researcher(s) with significant contributions to the overviewed sub-area.In the introductory chapter, Sophia Ananiadou and John McNaught adhere to the definition of text mining by Hearst (p.1), although their interpretation lays more emphasis on the unstructured nature of the input textual data than on the potential novelty of the output information.Those "interested in organizing, searching, discovering, or communicating biological knowledge" (p. 2) are the targeted readers of the book.The book aims to provide them with an "extensive summarization and discussion of the research literature in text mining and reported systems, geared towards informing and educating rather than oriented towards other text mining experts" (p.3).Information retrieval is placed outside the scope of the book, which focuses on performing familiar tasks such as named entity recognition (NER) and information extraction (IE) on biomedical text, but also extensively discusses problems that are less studied in general NLP but are of particular importance in this area, such as the exploitation of domain-specific knowledge sources, the construction of terminologies, how to deal with abbreviations, and so on.An outline of the main aims and challenges in biomedical NLP is followed by an overview of how these issues are discussed in each chapter.Chapter 2, "Levels of natural language processing for text mining" by Udo Hahn and Joachim Wermter, first explains how each level of linguistic analysis (i.e., morphology, syntax, and semantics) is associated with distinct NLP components.Then a

This paper describes a novel computer-aided procedure for generating multiple-choice test items from electronic documents. In addition to employing various Natural Language Processing techniques, including shallow parsing, automatic term extraction, sentence transformation and computing of semantic distance, the system makes use of language resources such as corpora and ontologies. It identifies important concepts in the text and generates questions about these concepts as well as multiple-choice distractors, offering the user the option to post-edit the test items by means of a user-friendly interface. In assisting test developers to produce items in a fast and expedient manner without compromising quality, the tool saves both time and production costs.

We present the first algorithm that computes optimal orderings of sentences into a locally coherent discourse. The algorithm runs very efficiently on a variety of coherence measures from the literature. We also show that the discourse ordering problem is NP-complete and cannot be approximated.

We use a reliably annotated corpus to compare metrics of coherence based on Centering Theory with respect to their potential usefulness for text structuring in natural language generation. Previous corpus-based evaluations of the coherence of text according to Centering did not compare the coherence of the chosen text structure with that of the possible alternatives. A corpus-based methodology is presented which distinguishes between Centering-based metrics taking these alternatives into account, and represents therefore a more appropriate way to evaluate Centering from a text structuring perspective.