Real versus Template-Based Natural Language Generation: A False Opposition?
نویسندگان
چکیده
Natural language generation (NLG) systems are sometimes partitioned into applicationdependent systems which lack a proper theoretical foundation, on the one hand, and theoretically well-founded systems which embody generic linguistic insights, on the other. Template-based systems are often regarded as automatically falling into the first category. We argue against this view. First, we describe the received view of both template-based and ‘‘standard’’ NLG systems (section 2). Then we describe a class of recent template-based systems (section 3) that will serve as a basis for a comparison between template-based and other NLG systems with respect to their potential for performing NLG tasks (section 4). We ask what the real difference between templatebased and other systems is and argue that the distinction between the two is becoming increasingly blurred (section 5). Finally, we discuss the implications of engineering shortcuts (Mellish 2000) and corpus-based methods (section 6).
منابع مشابه
Pipelines, Templates and Transformations: XML for Natural Language Generation
The paper discusses a number of ways in which XML can be used in natural language generation, including XML-based pipeline architectures, template-based generation with XSL templates, and tree-totree transformations. The ideas are based on practical experience in building an experimental XMLbased generation component for a spoken dialogue system. Prototype implementations using DOM, XSL and Tra...
متن کاملApplying Semantic Frame Theory to Automate Natural Language Template Generation From Ontology Statements
Today there exist a growing number of framenet-like resources offering semantic and syntactic phrase specifications that can be exploited by natural language generation systems. In this paper we present on-going work that provides a starting point for exploiting framenet information for multilingual natural language generation. We describe the kind of information offered by modern computational...
متن کاملSyntactic Generation of Arabic in Interlingua-based Machine Translation Framework
Arabic is a highly inflectional language, with a rich morphology, relatively free word order, and two types of sentences: nominal and verbal. Arabic natural language processing in general is still underdeveloped and Arabic natural language generation (NLG) is even less developed. In particular, Arabic natural language generation from Interlingua was only investigated using template-based approa...
متن کاملJYAG & IDEY: A Template-Based Generator and Its Authoring Tool
JYAG (Java 2.0 Platform YAG) is the Java implementation of a real-time, general-purpose, template-based generation system (YAG, Yet Another Generator) (Channarukul 1999; McRoy, Channarukul, & Ali 2000). JYAG enables interactive applications to adapt natural language output to the interactive context without requiring developers to write all possible output strings ahead of time or to embed exte...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- Computational Linguistics
دوره 31 شماره
صفحات -
تاریخ انتشار 2005