Standard context-aware neural machine translation (NMT) typically relies on
parallel document-level data, exploiting both source and target contexts.
Concatenation-based approaches in particular, still a strong baseline for
document-level NMT, prepend source and/or target context sentences to the
sentences to be translated, with model variants that exploit equal amounts of
source and target data on each side achieving state-of-the-art results. In this
work, we investigate whether target data should be further promoted within
standard concatenation-based approaches, as most document-level phenomena rely
on information that is present on the target language side. We evaluate novel
concatenation-based variants where the target context is prepended to the
source language, either in isolation or in combination with the source context.
Experimental results in English-Russian and Basque-Spanish show that including
target context in the source leads to large improvements on target language
phenomena. On source-dependent phenomena, using only target language context in
the source achieves parity with state-of-the-art concatenation approaches, or
slightly underperforms, whereas combining source and target context on the
source side leads to significant gains across the board.

该研究通过拼接语境的方法，研究了在标准文档级神经机器翻译中，是否应进一步提升目标语言的上下文对翻译结果的影响，实验结果表明，在目标语言现象上，将目标语言上下文加入到源语言端能够有显著的提升，而在依赖于源语言的现象方面，将源语言和目标语言的上下文同时加入源语言端能够在所有指标上都有显著的提升。

上下文感知的神经机器翻译中的目标数据推广

Promoting Target Data in Context-aware Neural Machine Translation

State-of-the-art (SOTA) neural machine translation (NMT) systems translate
texts at sentence level, ignoring context: intra-textual information, like the
previous sentence, and extra-textual information, like the gender of the
speaker. Because of that, some sentences are translated incorrectly.
Personalised NMT (PersNMT) and document-level NMT (DocNMT) incorporate this
information into the translation process. Both fields are relatively new and
previous work within them is limited. Moreover, there are no readily available
robust evaluation metrics for them, which makes it difficult to develop better
systems, as well as track global progress and compare different methods. This
thesis proposal focuses on PersNMT and DocNMT for the domain of dialogue
extracted from TV subtitles in five languages: English, Brazilian Portuguese,
German, French and Polish. Three main challenges are addressed: (1)
incorporating extra-textual information directly into NMT systems; (2)
improving the machine translation of cohesion devices; (3) reliable evaluation
for PersNMT and DocNMT.

Personalised NMT and document-level NMT are proposed to incorporate extra-textual information directly into the machine translation process, with the aim of improving the accuracy of translation for subtitles in five languages, respectively. The main challenges are addressed by incorporating extra-textual information, improving the accuracy of cohesion devices, and proposing reliable evaluation metrics for PersNMT and DocNMT.

面向个性化及文档级对话机器翻译

Towards Personalised and Document-level Machine Translation of Dialogue

Previous works have shown that contextual information can improve the
performance of neural machine translation (NMT). However, most existing
document-level NMT methods only consider a few number of previous sentences.
How to make use of the whole document as global contexts is still a challenge.
To address this issue, we hypothesize that a document can be represented as a
graph that connects relevant contexts regardless of their distances. We employ
several types of relations, including adjacency, syntactic dependency, lexical
consistency, and coreference, to construct the document graph. Then, we
incorporate both source and target graphs into the conventional Transformer
architecture with graph convolutional networks. Experiments on various NMT
benchmarks, including IWSLT English--French, Chinese-English, WMT
English--German and Opensubtitle English--Russian, demonstrate that using
document graphs can significantly improve the translation quality. Extensive
analysis verifies that the document graph is beneficial for capturing discourse
phenomena.

利用图形化表示法将文档作为全局语境，并将其整合到传统的变压器架构中，结合多种关系，包括邻接，句法依赖，词汇一致性和指代，能够显著提高神经机器翻译的性能。