TAILIEUCHUNG - Báo cáo khoa học: "Combining Multiple, Large-Scale Resources in a Reusable Lexicon for Natural Language Generation"

A lexicon is an essential component in a generation system but few efforts have been made to build a rich, large-scale lexicon and make it reusable for different generation applications. In this paper, we describe our work to build such a lexicon by combining multiple, heterogeneous linguistic resources which have been developed for other purposes. Novel transformation and integration of resources is required to reuse them for generation. We also applied the lexicon to the lexical choice and realization component of a practical generation application by using a multi-level feedback architecture. . | Combining Multiple Large-Scale Resources in a Reusable Lexicon for Natural Language Generation Hongyan Jing and Kathleen McKeown Department of Computer Science Columbia University New York NY 10027 USA hjing kathy @ Abstract A lexicon is an essential component in a generation system but few efforts have been made to build a rich large-scale lexicon and make it reusable for different generation applications. In this paper we describe our work to build such a lexicon by combining multiple heterogeneous linguistic resources which have been developed for other purposes. Novel transformation and integration of resources is required to reuse them for generation. We also applied the lexicon to the lexical choice and realization component of a practical generation application by using a multi-level feedback architecture. The integration of the lexicon and the architecture is able to effectively improve the system paraphrasing power minimize the chance of grammatical errors and simplify the development process substantially. 1 Introduction Every generation system needs a lexicon and in almost every case it is acquired anew. Few efforts in building a rich large-scale and reusable generation lexicon have been presented in literature. Most generation systems are still supported by a small system lexicon with limited entries and hand-coded knowledge. Although such lexicons are reported to be sufficient for the specific domain in which a generation system works there are some obvious deficiencies 1 Hand-coding is time and labor intensive and introduction of errors is likely. 2 Even though some knowledge such as syntactic structures for a verb is domain-independent often it is re-encoded each time a new application is under development. 3 Hand-coding seriously restricts the scale and expressive power of generation systems. As natural language generation is used in more ambitious applications this sit uation calls for an improvement. Generally existing linguistic .

• Báo cáo khoa học
• Combining Multiple
• Large Scale Resources in a Reusable Lexicon
• Natural Language Generation
• báo cáo khoa học
• mô hình ngôn ngữ
• xử lý ngôn ngữ tự nhiên
• Combining Multiple Resources
• Improve SMT based Paraphrasing Model
• Shiqi Zhao
• báo cáo ngôn ngữ
• Combining Multiple Knowledge Sources
• Dialogue Segmentation
• Multimedia Archives
• Knowledge Sources
• Discourse Segmentation
• Improved Lexical Alignment
• Combining Multiple Reified Alignments
• Dan Tufi
• scientific reports
• model language
• process natural language
• BMC Bioinformatics
• Missing variants
• Combining multiple bioinformatics pipelines
• Rare variants
• Identifying risk factors
• Plankton classification
• Image classification
• Multiple view features
• Feature selection
• Multiple kernel learning
• Multiple tissues
• Score test
• Tissue specificity
• Combining genetic
• O methyl transferase
• Microarray technology
• Microarray meta analysis
• Multiple microarray
• Biological hypotheses
• Meta analysis methods
• Cancer genome
• Somatic mutation calling
• Combining calls
• Systematically outperforms
• Báo cáo sinh học hay
• cách trình bày báo cáo
• báo cáo sinh học
• công trình nghiên cứu sinh học
• tài liệu về sinh học
• báo cáo hóa học
• công trình nghiên cứu về hóa học
• tài liệu về hóa học
• Genomic relationship matrix
• Genomic selection
• Disease risk prediction
• Best linear unbiased estimate
• BMC Genomics
• Efficient data integration
• Genome wide NGS
• NGS data analysis
• Minimum Bayes factor
• Successive interference cancellation
• Superposition coding
• Power allocation
• Underlay cognitive radio
• Non orthogonal multiple access
• Outage probability
• Genome annotation
• Functional annotation
• Enzyme prediction
• Transport prediction
• Metabolic modeling