解释建模：通过推理句子隐含的道德判断实现句子的社会锚定
Interpretation modeling: Social grounding of sentences by reasoning over their implicit moral judgments
AI总结：
本文提出解释建模任务，通过社会关系、共同背景及隐含道德判断的多重标注，结合一对一与一对多生成方法建模句子的多元合理解释，并以数据集、自动与人工评估及毒性分析验证其挑战与内容安全价值。
摘要：
人类交流的社会性和隐含性会影响读者对书面句子的理解。单一的黄金标准解释很少存在，这对自然语言处理中的传统假设构成挑战。本文提出解释建模（interpretation modeling，IM）任务，该任务涉及对一个句子底层语义的多种解释进行建模，以发掘隐含意义的不同层次。为获得这些解释，IM 以社会关系和共同背景的多重标注为指导；在本研究中，这些要素由读者对作者的态度以及读者对句子中微妙嵌入的道德判断的理解来近似。我们提出了若干建模策略，这些策略依赖一对一和一对多生成方法，并从关于解释的哲学研究中获得启发。研究构建了一个同类首个 IM 数据集，以支持实验和分析。建模结果以及对数据集的细致考察凸显了 IM 的挑战，因为相互冲突且复杂的解释在社会层面上都是合理的。对生成解释的自动评估和人工评估都证实了这种多元解读之间的相互作用。最后，对生成解释的毒性分析表明，IM 对于改进内容过滤器以及协助内容审核者维护在线讨论安全具有重要意义。
英文摘要：
The social and implicit nature of human communication ramifies readers' understandings of written sentences. Single gold-standard interpretations rarely exist, challenging conventional assumptions in natural language processing. This work introduces the interpretation modeling (IM) task which involves modeling several interpretations of a sentence's underlying semantics to unearth layers of implicit meaning. To obtain these, IM is guided by multiple annotations of social relation and common ground - in this work approximated by reader attitudes towards the author and their understanding of moral judgments subtly embedded in the sentence. We propose a number of modeling strategies that rely on one-to-one and one-to-many generation methods that take inspiration from the philosophical study of interpretation. A first-of-its-kind IM dataset is curated to support experiments and analyses. The modeling results, coupled with scrutiny of the dataset, underline the challenges of IM as conflicting and complex interpretations are socially plausible. This interplay of diverse readings is affirmed by automated and human evaluations on the generated interpretations. Finally, toxicity analyses in the generated interpretations demonstrate the importance of IM for refining filters of content and assisting content moderators in safeguarding the safety in online discourse.
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。
