Conceptual Revision for Natural Language Generation
نویسنده
چکیده
Traditional natural language generation systems are based on a pipelined architecture. A conceptual component selects items from a knowledge base and orders them into a message to address some discourse goal. This message is passed to the stylistic component that makes lexical and syntactic choices to produce a natural language surface text. By contrast, humans producing formal text typically create drafts which they polish through revision [Hayes and Flower 1980]. One proposal for improving the quality of computer-generated multisentential text is to incorporate a draft-and-revision paradigm.
منابع مشابه
Kalos - A Syste for Natural Language Generatio with Revision
Using revision to produce extended natural language text through a series of drafts provides three significant advantages over a traditional natural language generation system. First, it reduces complexity through task decomposition. Second, it promotes text polishing techniques that benefit from the ability to examine generated text in the context of the underlying knowledge from which it was ...
متن کاملMultilingual Revision
Natural Language Generation has made great strides towards multilingual generation from large-scale knowledge sources. Meanwhile, current research in revision has vastly improved the quality of text that NLG systems produce. However, to-date there has been no attempt at combining revision and multilingual NLG. This paper presents research in multilingual revision, the last major pipelined NLG c...
متن کاملText Polishing: Surface-Oriented Smoothing of Generated Text via Markup-Based Revision Rules
In this paper, we introduce text polishing, a novel, surface-oriented approach to using revisions in natural language generation in order to improve the fluency of generated texts. In this approach, markupbased revision rules are used to implement sentence planning operations such as aggregation, referring expression generation and discourse marker insertion. By working close to the surface, we...
متن کاملRevision : A Model and Its Implementation
To generate good text, many kinds of decisions should be made. Many researchers have spent much time searching for the architecture that would determine a proper order for these decisions. However, even if such an architecture is found, there are still certain kinds of problems that are dicult to consider during the generation process. Those problems can be more easily detected and solved by in...
متن کاملA Model of Revision in Natural Language Generation
We outline a model of generation with revision, focusing on improving textual coherence. We argue that high quality text is more easily produced by iteratively revising and regenerating, as people do, rather than by using an architecturally more complex single pass generator. As a general area of study, the revision process presents interesting problems: Recognition of flaws in text requires a ...
متن کامل