With the proliferation of short video applications, the significance of short video recommendations has vastly increased. Unlike other recommendation scenarios, short video recommendation systems heavily rely on feedback from watch time. Existing approaches simply treat watch time as a direct label, failing to effectively harness its extensive semantics and introduce bias, thereby limiting the potential for modeling user interests based on watch time. To overcome this challenge, we propose a framework named Debiasied Multiple-semantics-extracting Labeling (DML). DML constructs labels that encompass various semantics by utilizing quantiles derived from the distribution of watch time, prioritizing relative order rather than absolute label values. This approach facilitates easier model learning while aligning with the ranking objective of recommendations. Furthermore, we introduce a method inspired by causal adjustment to refine label definitions, thereby reducing the impact of bias on the label and directly mitigating bias at the label level. We substantiate the effectiveness of our DML framework through both online and offline experiments. Extensive results demonstrate that our DML could effectively leverage watch time to discover users' real interests, enhancing their engagement in our application.

翻译：随着短视频应用的普及，短视频推荐的重要性显著提升。与其他推荐场景不同，短视频推荐系统高度依赖观看时长反馈。现有方法简单地将观看时长作为直接标签使用，未能有效利用其丰富的语义信息，且引入偏差，从而限制了基于观看时长建模用户兴趣的潜力。为克服这一挑战，我们提出名为去偏多语义提取标签（DML）的框架。DML通过利用观看时长分布中的分位数构建包含多种语义的标签，优先考虑相对顺序而非绝对标签值。这种方法有助于模型学习，同时与推荐的排序目标一致。此外，我们引入一种受因果调整启发的方法来优化标签定义，从而降低偏差对标签的影响，并直接在标签层面缓解偏差。我们通过在线和离线实验验证了DML框架的有效性。大量结果表明，我们的DML能够有效利用观看时长发现用户的真实兴趣，提升其在应用程序中的参与度。