Quotation Recommendation for Multi-Party Online Conversations based on Semantic and Topic Fusion

Quotations are crucial for successful explanations and persuasions in interpersonal communications. However, finding what to quote a conversation is challenging humans. This work studies automatic quotation recommendation online conversations. Unlike the previous works that only consider semantic-level modeling, we adopt topic-level representation facilitate recommendation. A hierarchical architecture based on pretrained language model adopted representation, neural topic employed learn representation. Moreover, modeling enhanced by topic-aware attention mechanism, which capture interactive structure from perspective of word co-occurrence. The joint training semantic- topic-based leads significantly better performance than state-of-the-art models two large-scale datasets. Apart novel advanced framework, conduct extensive quantitative experiments investigate difficulty task, validate assumption, explore stability Some qualitative analyses also included interpret distribution some instances. All provide persuasive interpretations module design results.