Imagen de Portada

An Energy-based Model for Word-level AutoCompletion in Computer-aided Translation

Guardado en:
Publicado en:arXiv.org (Jul 29, 2024), p. n/a
Autor principal: Cheng, Yang
Otros Autores: Huang, Guoping, Yu, Mo, Zhang, Zhirui, Li, Siheng, Yang, Mingming, Shi, Shuming, Yang, Yujiu, Liu, Lemao
Publicado:
Cornell University Library, arXiv.org
Materias:
Labels
Machine translation
Computer aided mapping
Neural networks
Context
Sentences
Effectiveness
Acceso en línea:Citation/Abstract
Full text outside of ProQuest
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
Resumen:Word-level AutoCompletion(WLAC) is a rewarding yet challenging task in Computer-aided Translation. Existing work addresses this task through a classification model based on a neural network that maps the hidden vector of the input context into its corresponding label (i.e., the candidate target word is treated as a label). Since the context hidden vector itself does not take the label into account and it is projected to the label through a linear classifier, the model can not sufficiently leverage valuable information from the source sentence as verified in our experiments, which eventually hinders its overall performance. To alleviate this issue, this work proposes an energy-based model for WLAC, which enables the context hidden vector to capture crucial information from the source sentence. Unfortunately, training and inference suffer from efficiency and effectiveness challenges, thereby we employ three simple yet effective strategies to put our model into practice. Experiments on four standard benchmarks demonstrate that our reranking-based approach achieves substantial improvements (about 6.07%) over the previous state-of-the-art model. Further analyses show that each strategy of our approach contributes to the final performance.
ISSN:2331-8422
DOI:10.1162/tacl_a_00637
Fuente:Engineering Database