User-Controlled, Robust Natural Language Generation from an Evolving Knowledge Base
نویسندگان
چکیده
In this paper we describe a natural language generation system which produces complex sentences from a biology knowledge base. The NLG system allows domain experts to discover errors in the knowledge base and generates certain parts of answers in response to users’ questions in an e-textbook application. The system allows domain experts to customise its lexical resources and to set parameters which influence syntactic constructions in generated sentences. The system is capable of dealing with certain types of incomplete inputs arising from a knowledge base which is constantly edited and includes a referring expression generation module which keeps track of discourse history. Our referring expression module is available for download as the open source Antfarm tool1.
منابع مشابه
A Logical-Form and Knowledge-Base Design for Natural Language Generation
This paper presents a technique for interpreting output demands by a natural language sentence generator in a formally transparent and efficient way. These demands are stated in a logical language. A network knowledge base organizes the concepts of the application domain into categories known to the generator. The logical expressions are interpreted by the generator using the knowledge base and...
متن کاملA Natural Language Argumentation Interface for Explanation Generation in Markov Decision Processes
A Markov Decision Process (MDP) policy presents, for each state, an action, which preferably maximizes the expected reward accrual over time. In this paper, we present a novel system that generates, in real time, natural language explanations of the optimal action, recommended by an MDP while the user interacts with the MDP policy. We rely on natural language explanations in order to build trus...
متن کاملSentence Ordering in Electronic Navigational Chart Companion Text Generation
We present the sentence ordering part of a natural language generation module, used in the framework of a knowledge base of electronic navigation charts and sailing directions. The particularity of the knowledge base is that it is based on a controlled hybrid language, that is the combination of a controlled natural language and a controlled visual language. The sentence ordering process is abl...
متن کاملIntroducing a Multi-Dimensional User Model to Tailor Natural Language Generation
Previous work has shown that it is important to include user modeling in question answering systems in order to tailor the output. In this thesis, we develop a natural language response generation model that handles both definitional and procedural questions, and employs a multi-dimensional user model. The various attributes of the user recorded in the user model include the user’s role, domain...
متن کاملControlled natural languages for interface agents
Restrictions on the user interface (like using templateor menu-based communication ) could significantly ease the implementation but they constrain considerably the expressiveness, the flexibility and the applicability. Building free-form natural language communication with domain restrictions is also possible but it requires the application of very complex language tools (parsing, disambiguati...
متن کامل