我们有一个严肃的翻译：将互理解建模为概率推理
We Hebben Een Serieus Translatie: Modeling Intercomprehension as Probabilistic Inference
浏览论文内容
中文总结 AI 辅助
研究如何实现零样本跨语言理解，通过扩展噪声信道推理算法模型，在贝叶斯框架下建模互理解，用L1语言模型和通用噪声模型推断L2与L1单词映射，实验表明完整模型性能优于消融模型及大模型零样本提示。
中文摘要 AI 辅助
互理解是指一种相关语言（L1）的使用者对不熟悉语言（L2）的部分可理解性。这种零样本跨语言理解是如何实现的？在这项工作中，我们扩展了以往关于噪声信道推理算法模型的工作，在贝叶斯框架中对互理解进行建模。该模型仅使用L1中的语言模型对观察到的L2话语的翻译潜在假设进行评分，并使用通用噪声模型根据基于形式的相似性或符号规则推断L2和L1单词之间的映射。然后，我们进行了一项人类行为实验，分别从英语、西班牙语和俄语使用者那里引出对荷兰语、意大利语和乌克兰语话语的推理。我们的完整模型比消融模型更符合人类互理解性能的分布，并且与大得多的模型的零样本提示相比也更具优势。这些结果提供了一个认知上合理的互理解计算模型，并突出了理解者在现实世界跨语言场景中广泛不确定性下所做的灵活推理。我们公开分享了我们的代码。
英文摘要
Intercomprehension refers to partial intelligibility of an unfamiliar language (L2) by a speaker of a related language (L1). How is this zero-shot cross-language comprehension possible? In this work, we extend past work on algorithmic models of noisy-channel inference to model intercomprehension in a Bayesian framework. The model uses an LM in L1 only for scoring latent hypotheses about the translations of observed L2 utterances, and a general-purpose noise model to infer a mapping between L2 and L1 words based on either form-based similarity or symbolic rules. We then conduct a human behavioral experiment, eliciting inferences for utterances in Dutch, Italian, and Ukrainian from speakers of English, Spanish, and Russian, respectively. Our full model shows a closer alignment to the distribution of human intercomprehension performance than ablations, and also compares favorably to zero-shot prompting of much larger models. These results provide a cognitively plausible computational model of intercomprehension, and highlight the flexible inferences made by comprehenders under wide uncertainty in real-world cross-language scenarios. We share our code publicly.
