Spatial representation of context-dependent sentences and its application to sentence generation

Autor:	Wataru Takano, Tomoyuki Maekawa
Rok vydání:	2017
Předmět:	Space (punctuation) 0209 industrial biotechnology Japanese grammar Computer science media_common.quotation_subject Speech recognition Context (language use) 02 engineering and technology computer.software_genre Set (abstract data type) 020901 industrial engineering & automation 0202 electrical engineering electronic engineering information engineering media_common Sequence Grammar business.industry Text segmentation Computer Science Applications Human-Computer Interaction TheoryofComputation_MATHEMATICALLOGICANDFORMALLANGUAGES Hardware and Architecture Control and Systems Engineering ComputingMethodologies_DOCUMENTANDTEXTPROCESSING 020201 artificial intelligence & image processing Artificial intelligence business computer Software Sentence Natural language processing
Zdroj:	Advanced Robotics. 31:780-790
ISSN:	1568-5535 0169-1864
Popis:	We propose a novel approach to embedding sentences into a high-dimensional space. Independent words in the sentence are located at points in the space, and the sentence is represented by a curve along these words. A set of functions that evaluates a sequence of words is designed over this space and is helpful for searching for words that are likely to follow the observed sentences. More generally, our approach makes sentences sequentially depending on the context. We simplify Japanese grammar and subsequently implement it as a grammar that constrains simple sentences to be generated. In this study, we performed experiments in which we created a dictionary containing 2877 different independent words and constructed a semantic space from texts in eight digital archived books, consisting of 8495 independent words and 161 paragraphs in total. It was demonstrated that several meaningful sentences can be generated that are likely to follow untrained input sentences.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::a2fd1f0c8aa6eea27d6abce55bd98a8a https://doi.org/10.1080/01691864.2017.1351392 Zobrazit plný text záznamu Plný text ve formátu PDF Plný text ve formátu HTML
Nepřihlášeným uživatelům se plný text nezobrazuje	K zobrazení výsledku je třeba se přihlásit.