Improving Rare Word Translation With Dictionaries and Attention Masking

Autor:	Sible, Kenneth J., Chiang, David
Rok vydání:	2024
Předmět:	Computer Science - Computation and Language Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	In machine translation, rare words continue to be a problem for the dominant encoder-decoder architecture, especially in low-resource and out-of-domain translation settings. Human translators solve this problem with monolingual or bilingual dictionaries. In this paper, we propose appending definitions from a bilingual dictionary to source sentences and using attention masking to link together rare words with their definitions. We find that including definitions for rare words improves performance by up to 1.0 BLEU and 1.6 MacroF1. Comment: 11 pages, 3 figures, 3 tables. Accepted at AMTA 2024
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2408.09075 Zobrazit plný text záznamu View this record from Arxiv