Robust Multimodal Sentiment Analysis with Incomplete Modalities via Semantic-aware Completeness based Reconstruction

The paper presents a method for robust multimodal sentiment analysis that handles incomplete or noisy modalities. It introduces a completeness estimation technique to measure how much sentiment-relevant information remains in partial data, guiding the reconstruction of missing semantics. A joint training strategy stabilizes multi-task learning for sentiment prediction and completeness estimation, and experiments on three benchmark datasets show improved semantic reconstruction and sentiment accuracy.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

• nlp
• multimodal
• benchmarks