Name: Robust Semantic Role Labeling: Robust Semantic Role Labeling: Using Parsing Variations and Semantic Classes (en Inglés)
Price: 91.19 USD
Availability: InStock
Author: Szu-Ting Yi
ISBN: 9783659691966

portada Robust Semantic Role Labeling: Robust Semantic Role Labeling: Using Parsing Variations and Semantic Classes (en Inglés)

Robust Semantic Role Labeling: Robust Semantic Role Labeling: Using Parsing Variations and Semantic Classes (en Inglés)

Formato

Libro Físico

Editorial

Lap Lambert Academic Publishing

Autor

Szu-Ting Yi

Idioma

Inglés

N° páginas

172

Encuadernación

Tapa Blanda

ISBN13

9783659691966

Robust Semantic Role Labeling: Robust Semantic Role Labeling: Using Parsing Variations and Semantic Classes (en Inglés)

Szu-Ting Yi (Autor) · Lap Lambert Academic Publishing · Tapa Blanda

Libro Nuevo Importado

Envío: 25 a 32 días háb.

$ 165.79$ 91.19

-45%

Costos de importación incluídos en el precio ✅

Libro Nuevo

Quedan 10 unidades

$ 91.19

Llega entre el 16 Sep y el 29 Sep a Quito, Pichincha. Seleccionar ubicación

Agregar a lista de deseos

Reseña del libro "Robust Semantic Role Labeling: Robust Semantic Role Labeling: Using Parsing Variations and Semantic Classes (en Inglés)"

Correctly identifying semantic entities and successfully disambiguating the relations between them and their predicates is an important and necessary step for successful natural language processing applications, such as text summarization, question answering, and machine translation. Researchers have studied this problem, semantic role labeling (SRL), as a machine learning problem since 2000. However, after using an optimal global inference algorithm to combine several SRL systems, the growth of SRL performance seems to have reached a plateau. Syntactic parsing is the bottleneck of the task of semantic role labeling and robustness is the ultimate goal. In this book, we investigate ways to train a better syntactic parser and increase SRL system robustness. We demonstrate that parse trees augmented by semantic role markups can serve as suitable training data for training a parser for an SRL system. For system robustness, we propose that it is easier to learn a new set of semantic roles. The new roles are less verb- dependent than the original PropBank roles. As a result, the SRL system trained on the new roles achieves significantly better robustness.