Visualising discourse coherence in non-linear documents

نویسندگان

  • Clara Mancini
  • Donia Scott
  • Simon Buckingham Shum
چکیده

To produce coherent linear documents, Natural Language Generation systems have traditionally exploited the structuring role of textual discourse markers such as relational and referential phrases. These coherence markers of the traditional notion of text, however, do not work in non-linear documents: a new set of graphical devices is needed together with formation rules to govern their usage, supported by sound theoretical frameworks. If in linear documents graphical devices such as layout and formatting complement textual devices in the expression of discourse coherence, in non-linear documents they play a more important role. In this paper, we present our theoretical and empirical work in progress, which explores new possibilities for expressing coherence in the generation of hypertext documents. RÉSUMÉ. Dans la production de documents linéaires, les systèmes de Génération Automatique du Langage ont traditionnellement exploité le rôle structurel des marques textuelles du discours, comme les phrases relationnelles et référentielles. Pourtant, ces marques de la cohérence textuelle ne fonctionnent pas dans des documents non linéaires: des nouveaux dispositifs graphiques sont nécessaires avec des règles d’utilisation guidées par des structures théoriques. Si des dispositifs graphiques comme composition et formatage contribuent á l’expression de la cohérence dans des documents linéaires, leur rôle est beaucoup plus important dans des documents non-linéaires. Dans cet article nous explorons des nouvelles possibilités pour représenter la cohérence dans des documents hypertextuels.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Visualising discourse coherence in non-linear document generation

In order to produce coherent linear documents, Natural Language Generation (NLG) systems have traditionally exploited the structuring role played by textual discourse markers such as relational and referential phrases. However, these coherence markers of the traditional notion of text do not work as efficiently in non-linear informative documents, where ambiguity and indeterminacy are usually u...

متن کامل

Hyper-Document Structure: Maintaining Discourse Coherence in Non-Linear Documents

The passage from linear text to hypertext poses the challenge of expressing discourse coherence in non-linear text, where linguistic discourse markers no longer work. While hypertext introduces new possibilities for discourse organisation, it also requires the use of new devices which can support the expression of coherence by exploiting the technical characteristics and expressive richness of ...

متن کامل

Modelling Compression with Discourse Constraints

Sentence compression holds promise for many applications ranging from summarisation to subtitle generation. The task is typically performed on isolated sentences without taking the surrounding context into account, even though most applications would operate over entire documents. In this paper we present a discourse informed model which is capable of producing document compressions that are co...

متن کامل

Discourse Constraints for Document Compression

Sentence compression holds promise for many applications ranging from summarization to subtitle generation. The task is typically performed on isolated sentences without taking the surrounding context into account, even though most applications would operate over entire documents. In this article we present a discourse-informed model which is capable of producing document compressions that are ...

متن کامل

Visualising Search Result Sets Using a Force-Based Method to Form Clusters of Similar Documents

As human knowledge increases, so the volume of electronically available information grows. Finding specific information becomes more difficult and ever more matches are returned in response to a search query. Since quantity is seldom quality, numerous approaches to make sense of search result sets have been proposed. This thesis describes an approach called SearchVis to visualise search result ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:
  • TAL

دوره 47  شماره 

صفحات  -

تاریخ انتشار 2006