Better Captioning with Sequence-Level Exploration
This addresses a limitation in captioning models for generating more diverse and accurate descriptions, though it is incremental as it builds on existing sequence-level objectives.
The paper identified that current sequence-level learning objectives in captioning tasks only optimize precision, overlooking recall, and proposed adding a sequence-level exploration term to improve recall, showing effectiveness on video and image captioning datasets.
Sequence-level learning objective has been widely used in captioning tasks to achieve the state-of-the-art performance for many models. In this objective, the model is trained by the reward on the quality of its generated captions (sequence-level). In this work, we show the limitation of the current sequence-level learning objective for captioning tasks from both theory and empirical result. In theory, we show that the current objective is equivalent to only optimizing the precision side of the caption set generated by the model and therefore overlooks the recall side. Empirical result shows that the model trained by this objective tends to get lower score on the recall side. We propose to add a sequence-level exploration term to the current objective to boost recall. It guides the model to explore more plausible captions in the training. In this way, the proposed objective takes both the precision and recall sides of generated captions into account. Experiments show the effectiveness of the proposed method on both video and image captioning datasets.