Quotation Recommendation for Multi-party Online Conversations Based on Semantic and Topic Fusion
Open Access
- 28 July 2023
- journal article
- research article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 41 (4) , 1-27
Abstract
Quotations are crucial for successful explanations and persuasions in interpersonal communications. However, finding what to quote in a conversation is challenging for humans. This work studies automatic quotation recommendation for online conversations. Unlike the previous works that only consider semantic-level modeling, we adopt topic-level representation to facilitate the recommendation. A hierarchical architecture that is based on a pretrained language model is adopted to model the semantic-level conversation representation, and a neural topic model is employed to learn the topic-level representation. Moreover, the semantic-level conversation modeling is enhanced by a topic-aware attention mechanism, which is adopted to capture the interactive conversation structure from the perspective of word co-occurrence. The joint training of semantic- and topic-based recommendation leads to significantly better performance than the state-of-the-art models on two large-scale datasets. Apart from the novel and advanced recommendation framework, we conduct extensive quantitative experiments to investigate the difficulty of the quotation recommendation task, validate the topic-based recommendation assumption, and explore the stability of the recommendation. Some qualitative experiments and analyses are also included to interpret the quotation and topic distribution for some instances. All the extensive experiments and analyses provide persuasive explanations and interpretations of the module design and the recommendation results.Keywords
Funding Information
- CUHK (KPF23GWP20)
This publication has 31 references indexed in Scilit:
- Quote Recommendation in Dialogue using Deep Neural Network2016
- Using Content-level Structures for Summarizing Microblog Repost Trees2015
- Glove: Global Vectors for Word Representation2014
- Convolutional Neural Networks for Sentence Classification2014
- A Study of Idiom Translation Strategies between English and ChineseTheory and Practice in Language Studies, 2013
- Speech recognition with deep recurrent neural networks2013
- Fisher and Jensen–Shannon divergences: Quantitative comparisons among distributions. Application to position and momentum atomic densitiesThe Journal of Chemical Physics, 2009
- Finding high-quality content in social media2008
- Jensen-Shannon divergence as a measure of distinguishability between mixed quantum statesPhysical Review A, 2005
- Long Short-Term MemoryNeural Computation, 1997