arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2406.10091cs.CL
收藏

探索同声传译人工评估与机器评估之间的相关性

Exploring the Correlation between Human and Machine Evaluation of Simultaneous Speech Translation

University of Leeds(利兹大学);University of Mainz(美因茨大学)

Xiaoman Wang, Claudio Fantinuoli

AI总结:

本文以专家人工评分为基准,比较句嵌入与大型语言模型在无参考译文条件下评估同传忠实度的相关性,发现直接提示的GPT-3.5表现最佳且上下文窗口影响显著。

摘要:

鉴于口语翻译的细微特性、口译员采用的策略以及用户多样化的期望,评估口译服务的表现是一项复杂任务。当采用自动化评估方法时,这项任务的复杂性会更加突出。尤其如此,因为由于口译员所使用的策略,口译文本在源语言和目标语言之间表现出较弱的线性对应关系。本研究旨在通过分析自动指标与人工评估之间的相关性,评估其在评价同声传译时的可靠性。我们关注口译质量的一个特定特征,即翻译准确性或忠实度。我们将语言专家作出的人工评估作为基准,并评估句嵌入和大型语言模型与这些评估的相关程度。我们在不依赖参考译文的情况下,量化源文本与翻译文本之间的语义相似度。结果表明,GPT模型,尤其是采用直接提示的GPT-3.5,在源文本与目标文本之间语义相似度方面与人类判断表现出最强的相关性,即使在评估较短文本片段时也是如此。此外,研究揭示,上下文窗口的大小对这种相关性具有显著影响。

英文摘要:

Assessing the performance of interpreting services is a complex task, given the nuanced nature of spoken language translation, the strategies that interpreters apply, and the diverse expectations of users. The complexity of this task become even more pronounced when automated evaluation methods are applied. This is particularly true because interpreted texts exhibit less linearity between the source and target languages due to the strategies employed by the interpreter. This study aims to assess the reliability of automatic metrics in evaluating simultaneous interpretations by analyzing their correlation with human evaluations. We focus on a particular feature of interpretation quality, namely translation accuracy or faithfulness. As a benchmark we use human assessments performed by language experts, and evaluate how well sentence embeddings and Large Language Models correlate with them. We quantify semantic similarity between the source and translated texts without relying on a reference translation. The results suggest GPT models, particularly GPT-3.5 with direct prompting, demonstrate the strongest correlation with human judgment in terms of semantic similarity between source and target texts, even when evaluating short textual segments. Additionally, the study reveals that the size of the context window has a notable impact on this correlation.

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。

↑