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. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1109/TFUZZ.2022.3167129 | IEEE Transactions on Fuzzy Systems |
Keywords | DocType | Volume |
Data-driven global context,fuzzy bag-of-word (FBoW),intelligent translation system,target-side representation,translation memory (TM) | Journal | 30 |
Issue | ISSN | Citations |
11 | 1063-6706 | 0 |
PageRank | References | Authors |
0.34 | 14 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kehai Chen | 1 | 43 | 16.34 |
Yang Muyun | 2 | 112 | 29.50 |
Tiejun Zhao | 3 | 643 | 102.68 |
Min Zhang | 4 | 1849 | 157.00 |