This book explores the role of surface ambiguities in referring expressions, and how the risk of such ambiguities should be taken into account by an algorithm that generates referring expressions, if these expressions are to be optimally effective for a hearer. The main focus is on the ambiguities that arise when adjectives occur in coordinated structures (e.g. brown cats and dogs). The central idea is to use statistical information about lexical co-occurrence to estimate which interpretation of a phrase is most likely for human readers, and to avoid generating phrases where misunderstandings are likely. Various aspects of the problem were explored in a series of experiments, including a self-study paradigm. We found a preference for ''clear'' expressions to ''unclear'' ones, but if several of the expressions are ''clear,'' then brief expressions are preferred over non-brief ones even though the brief ones are syntactically ambiguous and the non-brief ones are not. The notion of clarity was made precise using Kilgarriff's Word Sketches. The results of these empirical studies motivated the design of a GRE algorithm.
Imtiaz Hussain Khan received his Masters (CS) and PhD (Artificial Intelligence) degrees from the University of Essex UK and University of Aberdeen UK, in 2005 and 2010, respectively. Since 2010, he has been working as an Assistant Professor at King Abdulaziz University, Saudi Arabia. His area of research is Natural Language Generation.
"Sobre este título" puede pertenecer a otra edición de este libro.
Gastos de envío:
EUR 3,57
A Estados Unidos de America
Librería: Lucky's Textbooks, Dallas, TX, Estados Unidos de America
Condición: New. Nº de ref. del artículo: ABLIING23Mar3113020287143
Cantidad disponible: Más de 20 disponibles
Librería: PBShop.store UK, Fairford, GLOS, Reino Unido
PAP. Condición: New. New Book. Delivered from our UK warehouse in 4 to 14 business days. THIS BOOK IS PRINTED ON DEMAND. Established seller since 2000. Nº de ref. del artículo: IQ-9783659465475
Cantidad disponible: 15 disponibles
Librería: PBShop.store US, Wood Dale, IL, Estados Unidos de America
PAP. Condición: New. New Book. Shipped from UK. THIS BOOK IS PRINTED ON DEMAND. Established seller since 2000. Nº de ref. del artículo: L0-9783659465475
Cantidad disponible: Más de 20 disponibles
Librería: Ria Christie Collections, Uxbridge, Reino Unido
Condición: New. PRINT ON DEMAND Book; New; Fast Shipping from the UK. No. book. Nº de ref. del artículo: ria9783659465475_lsuk
Cantidad disponible: Más de 20 disponibles
Librería: BuchWeltWeit Ludwig Meier e.K., Bergisch Gladbach, Alemania
Taschenbuch. Condición: Neu. This item is printed on demand - it takes 3-4 days longer - Neuware -This book explores the role of surface ambiguities in referring expressions, and how the risk of such ambiguities should be taken into account by an algorithm that generates referring expressions, if these expressions are to be optimally effective for a hearer. The main focus is on the ambiguities that arise when adjectives occur in coordinated structures (e.g. brown cats and dogs). The central idea is to use statistical information about lexical co-occurrence to estimate which interpretation of a phrase is most likely for human readers, and to avoid generating phrases where misunderstandings are likely. Various aspects of the problem were explored in a series of experiments, including a self-study paradigm. We found a preference for ''clear'' expressions to ''unclear'' ones, but if several of the expressions are ''clear,'' then brief expressions are preferred over non-brief ones even though the brief ones are syntactically ambiguous and the non-brief ones are not. The notion of clarity was made precise using Kilgarriff's Word Sketches. The results of these empirical studies motivated the design of a GRE algorithm. 148 pp. Englisch. Nº de ref. del artículo: 9783659465475
Cantidad disponible: 2 disponibles
Librería: AHA-BUCH GmbH, Einbeck, Alemania
Taschenbuch. Condición: Neu. nach der Bestellung gedruckt Neuware - Printed after ordering - This book explores the role of surface ambiguities in referring expressions, and how the risk of such ambiguities should be taken into account by an algorithm that generates referring expressions, if these expressions are to be optimally effective for a hearer. The main focus is on the ambiguities that arise when adjectives occur in coordinated structures (e.g. brown cats and dogs). The central idea is to use statistical information about lexical co-occurrence to estimate which interpretation of a phrase is most likely for human readers, and to avoid generating phrases where misunderstandings are likely. Various aspects of the problem were explored in a series of experiments, including a self-study paradigm. We found a preference for ''clear'' expressions to ''unclear'' ones, but if several of the expressions are ''clear,'' then brief expressions are preferred over non-brief ones even though the brief ones are syntactically ambiguous and the non-brief ones are not. The notion of clarity was made precise using Kilgarriff's Word Sketches. The results of these empirical studies motivated the design of a GRE algorithm. Nº de ref. del artículo: 9783659465475
Cantidad disponible: 1 disponibles
Librería: moluna, Greven, Alemania
Condición: New. Dieser Artikel ist ein Print on Demand Artikel und wird nach Ihrer Bestellung fuer Sie gedruckt. Autor/Autorin: Khan Imtiaz HussainImtiaz Hussain Khan received his Masters (CS) and PhD (Artificial Intelligence) degrees from the University of Essex UK and University of Aberdeen UK, in 2005 and 2010, respectively. Since 2010, he has been working. Nº de ref. del artículo: 5157774
Cantidad disponible: Más de 20 disponibles