HYPERBUG: A Scalable Natural Language Generation Approach
نویسنده
چکیده
A scalable natural language generation (NLG) system called HYPERBUG 1 embedded in an agent-based, multimodal dialog system is presented. To motivate this presentation, several scenarios (including a domain shift) are identified where scalability in dialog systems is really needed, and NLG is argued to be one way of easing this desired scalability. Therefore the novel approach to hybrid NLG in the HYPERBUG system is described and the scalability of its parts and resources is investigated. Concluding with a few remarks to discourse generation, we argue that NLG can both contribute to and benefit from scalability in dialog systems.
منابع مشابه
HYSSOP: Natural Language Generation Meets Knowledge Discovery in Databases
In this paper, we present HYSSOP, a system that generates natural language hypertext summaries of insights resulting from a knowledge discovery process. We discuss the synergy between the two technologies underlying HYSSOP: Natural Language Generation (NLG) and Knowledge Discovery in Databases (KDD). We first highlight the advantages of natural language hypertext as a summarization medium for K...
متن کاملFast, Scalable and Reliable Generation of Controlled Natural Language
In this paper we describe a natural language generation system which takes as its input a set of assertions encoded as a semantic graph and outputs a data structure connecting the semantic graph to a text which expresses those assertions, encoded as a TAG syntactic tree. The scope of the system is restricted to controlled natural language, and this allows the generator to work within a tightly ...
متن کاملLatent Predictor Networks for Code Generation
Many language generation tasks require the production of text conditioned on both structured and unstructured inputs. We present a novel neural network architecture which generates an output sequence conditioned on an arbitrary number of input functions. Crucially, our approach allows both the choice of conditioning context and the granularity of generation, for example characters or tokens, to...
متن کاملA New Method for Improving Computational Cost of Open Information Extraction Systems Using Log-Linear Model
Information extraction (IE) is a process of automatically providing a structured representation from an unstructured or semi-structured text. It is a long-standing challenge in natural language processing (NLP) which has been intensified by the increased volume of information and heterogeneity, and non-structured form of it. One of the core information extraction tasks is relation extraction wh...
متن کاملEvaluating the Robstness and Scalability of Revision-Based Natural Language Generation
This paper presents the rst quantitative, corpus-based evaluation of the same-domain robustness and scalability of a new revision-based language generation model, in comparison to the traditional single pass pipeline model. Robustness is deened as the proportion of sentences, in a given corpus test sample that can be generated using only knowledge structures abstracted from another sample. Scal...
متن کامل