Document-level Neural Machine Translation with Associated Memory Network
This work addresses the need for better document-level context modeling in machine translation, offering a novel method that is incremental but shows strong gains.
The paper tackled the problem of standard neural machine translation ignoring document-level context by proposing a document-aware memory network to exploit detailed context, resulting in significant performance improvements over strong Transformer baselines and related studies.
Standard neural machine translation (NMT) is on the assumption that the document-level context is independent. Most existing document-level NMT approaches are satisfied with a smattering sense of global document-level information, while this work focuses on exploiting detailed document-level context in terms of a memory network. The capacity of the memory network that detecting the most relevant part of the current sentence from memory renders a natural solution to model the rich document-level context. In this work, the proposed document-aware memory network is implemented to enhance the Transformer NMT baseline. Experiments on several tasks show that the proposed method significantly improves the NMT performance over strong Transformer baselines and other related studies.