arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.01416cs.CLcs.AIcs.LG
收藏

上下文感知机器翻译的序列缩短

Sequence Shortening for Context-Aware Machine Translation

Maastricht University(马斯特里赫特大学)

Paweł Mąka, Yusuf Can Semerci, Jan Scholtes, Gerasimos Spanakis

AI总结:

本研究针对上下文感知机器翻译,提出缓存源句潜在表示作为上下文的多编码器特例,并引入潜在分组与潜在选择两种序列缩短方法,在对比数据集上取得更高准确率,同时保持BLEU和COMET分数,提升可解释性并降低内存增长。

摘要:

上下文感知机器翻译旨在通过纳入周围句子作为上下文来改进句子的翻译。针对这一任务,已应用了两种主要架构,即单编码器(基于拼接)和多编码器模型。在本研究中,我们展示了多编码器架构的一个特例,其中源句子的潜在表示被缓存并在下一步中作为上下文重用,在对比数据集(模型必须在提供的句子中对正确翻译进行排序)上取得了更高的准确率,并且BLEU和COMET分数与单编码器和多编码器方法相当。此外,我们研究了序列缩短在缓存表示上的应用。我们测试了三种基于池化的缩短技术,并引入了两种新方法——潜在分组和潜在选择,其中网络学习对令牌进行分组或选择要作为上下文缓存的令牌。我们的实验表明,这两种方法在对比数据集上取得了与其他测试方法相当的BLEU和COMET分数和准确率,同时可能允许更高的可解释性,并减少随着上下文大小增加而增长的内存需求。

英文摘要:

Context-aware Machine Translation aims to improve translations of sentences by incorporating surrounding sentences as context. Towards this task, two main architectures have been applied, namely single-encoder (based on concatenation) and multi-encoder models. In this study, we show that a special case of multi-encoder architecture, where the latent representation of the source sentence is cached and reused as the context in the next step, achieves higher accuracy on the contrastive datasets (where the models have to rank the correct translation among the provided sentences) and comparable BLEU and COMET scores as the single- and multi-encoder approaches. Furthermore, we investigate the application of Sequence Shortening to the cached representations. We test three pooling-based shortening techniques and introduce two novel methods - Latent Grouping and Latent Selecting, where the network learns to group tokens or selects the tokens to be cached as context. Our experiments show that the two methods achieve competitive BLEU and COMET scores and accuracies on the contrastive datasets to the other tested methods while potentially allowing for higher interpretability and reducing the growth of memory requirements with increased context size.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑