作为连贯性维持的上下文学习:基于大语言模型的即时机器翻译研究
In-context Learning as Maintaining Coherency: A Study of On-the-fly Machine Translation Using Large Language Models
AI总结:
该研究以机器翻译为场景,提出上下文学习是生成任务与提示维持连贯性的视角,通过多模型多翻译方向实验验证提示与测试句的长期连贯性可预测翻译性能,证明了上下文机器翻译的即时适配有效性。
摘要:
上下文学习现象通常被认为是“从示例中学习”。在这项聚焦机器翻译的研究中,我们提出了一种视角:上下文学习是让目标生成任务与其上下文(即提示示例)维持连贯性。我们首先研究了跨4个领域的随机采样提示,发现当展示领域内提示时,翻译性能会提升。接下来,我们研究了领域内设置下的连贯性,该设置使用来自滑动窗口中的提示示例。我们结合文献中此前确定的其他因素(如长度、表面相似性和句子嵌入相似性)对此进行了研究。我们在3个模型(GPTNeo2.7B、Bloom3B、XGLM2.9B)以及3个翻译方向(英→{葡、德、法})上的结果表明,提示与测试句子的长期连贯性是下游翻译性能的良好指标。借此,我们证明了上下文机器翻译在即时适配方面的有效性。
英文摘要:
The phenomena of in-context learning has typically been thought of as "learning from examples". In this work which focuses on Machine Translation, we present a perspective of in-context learning as the desired generation task maintaining coherency with its context, i.e., the prompt examples. We first investigate randomly sampled prompts across 4 domains, and find that translation performance improves when shown in-domain prompts. Next, we investigate coherency for the in-domain setting, which uses prompt examples from a moving window. We study this with respect to other factors that have previously been identified in the literature such as length, surface similarity and sentence embedding similarity. Our results across 3 models (GPTNeo2.7B, Bloom3B, XGLM2.9B), and three translation directions (\texttt{en}$\rightarrow$\{\texttt{pt, de, fr}\}) suggest that the long-term coherency of the prompts and the test sentence is a good indicator of downstream translation performance. In doing so, we demonstrate the efficacy of In-context Machine Translation for on-the-fly adaptation.
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。