arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.03121cs.CL
收藏

通过语言模型将未来信息注入单调注意

Infusing Future Information into Monotonic Attention Through Language Models

Samsung Research(三星研究院)

Mohd Abbas Zaidi, Sathish Indurthi, Beomseok Lee, Nikhil Kumar Lakumarapu, Sangha Kim

摘要:

同步神经机器翻译(SNMT)模型在处理源序列之前就开始发射目标序列。SNMT的最新自适应策略使用单调注意来基于部分源和目标序列执行读/写决策。缺乏足够的信息可能会导致单调注意力做出糟糕的读/写决策,这反过来会对SNMT模型的性能产生负面影响。另一方面,人类翻译人员可以做出更好的读/写决策,因为他们可以使用语言信息和领域知识预测即将到来的单词。我们提出了一个框架,以帮助单调注意与外部语言模型,以改善其决策。我们进行实验的Must-C英语-德语和英语-法语语音到-文本翻译任务,以显示所提出的框架的有效性。所提出的SNMT方法提高了质量-延迟权衡比最先进的单调多头注意。

英文摘要:

Simultaneous neural machine translation(SNMT) models start emitting the target sequence before they have processed the source sequence. The recent adaptive policies for SNMT use monotonic attention to perform read/write decisions based on the partial source and target sequences. The lack of sufficient information might cause the monotonic attention to take poor read/write decisions, which in turn negatively affects the performance of the SNMT model. On the other hand, human translators make better read/write decisions since they can anticipate the immediate future words using linguistic information and domain knowledge.Motivated by human translators, in this work, we propose a framework to aid monotonic attention with an external language model to improve its decisions.We conduct experiments on the MuST-C English-German and English-French speech-to-text translation tasks to show the effectiveness of the proposed framework.The proposed SNMT method improves the quality-latency trade-off over the state-of-the-art monotonic multihead attention.

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。

↑