Data-Driven Fuzzy Target-Side Representation for Intelligent Translation System
Lists
Only you see this
Abstract
The encoder–decoder framework has been widely used in various practical artificial intelligence cyber-physical systems, including intelligent translation systems. The decoding process in such a framework usually demands the target-side representation, which is often learned by an autoaggressive decoder to simulate the target context information at the current time-step. However, the autoaggressive decoder only captures the previously generated partial target fragment and fails in simulating the global contextual information. In this article, we propose a new data-driven fuzzy context representation strategy to simulate the global target information. Specifically, we design two fuzzy methods to the global target contextual information, which are bag-of-words of target language generated via a softmax layer from the source-side representation and whole target sentence retrieved from the translation memory according to the source-side representation. Both methods facilitate the autoaggressive decoder to handle the global target context at the current time-step, thereby learning a more effective context vector for the generation of target translation. Extensive experiments on two machine translation tasks demonstrated that the proposed method achieved 3% improvement of BLEU score over a strong baseline.
BibTeX
@article{chen2022data,
author = {Kehai Chen and Muyun Yang and Tiejun Zhao and Min Zhang},
title = {{Data-Driven Fuzzy Target-Side Representation for Intelligent Translation System}},
journal = {IEEE Trans. Fuzzy Systems},
year = {2022},
url = {https://openreview.net/forum?id=asmebMwwx2},
}Loading related content...