论文标题
命名的实体检测和注射直接语音翻译
Named Entity Detection and Injection for Direct Speech Translation
论文作者
论文摘要
在句子中，某些词对其语义至关重要。其中，众所周知，指定的实体（NES）在神经模型中具有挑战性。尽管它们的重要性，但在语音到文本（S2T）翻译研究中，其准确的处理已被忽略，并且最近的工作表明，S2T模型在位置和尤其是人的名字方面表现较差，除非事先知道，否则其拼写具有挑战性。在这项工作中，我们探讨了如何利用已知可能出现在给定上下文中的NE的字典来改善S2T模型输出。我们的实验表明，我们可以可靠地检测到从S2T编码器输出开始的话语中可能存在的NE。确实，我们证明了当前的检测质量足以提高翻译中的NE准确性，而人名称错误降低了31％。
In a sentence, certain words are critical for its semantic. Among them, named entities (NEs) are notoriously challenging for neural models. Despite their importance, their accurate handling has been neglected in speech-to-text (S2T) translation research, and recent work has shown that S2T models perform poorly for locations and notably person names, whose spelling is challenging unless known in advance. In this work, we explore how to leverage dictionaries of NEs known to likely appear in a given context to improve S2T model outputs. Our experiments show that we can reliably detect NEs likely present in an utterance starting from S2T encoder outputs. Indeed, we demonstrate that the current detection quality is sufficient to improve NE accuracy in the translation with a 31% reduction in person name errors.
