Topic modeling on document networks with adjacent-encoder

• Main Authors: ZHANG, Ce, LAUW, Hady W.
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2020
• Subjects: Encoder architecture; Low-dimensional representation; Network structures; Semantic capture; Textual content; Topic Modeling; Artificial intelligence; Artificial Intelligence and Robotics; Databases and Information Systems
• Online Access: https://ink.library.smu.edu.sg/sis_research/5124; https://ink.library.smu.edu.sg/context/sis_research/article/6126/viewcontent/aaai20a.pdf
• Institution: Singapore Management University

Oftentimes documents are linked to one another in a network structure,e.g., academic papers cite other papers, Web pages link to other pages. In this paper we propose a holistic topic model to learn meaningful and unified low-dimensional representations for networked documents that seek to preserve both textual content and network structure. On the basis of reconstructing not only the input document but also its adjacent neighbors, we develop two neural encoder architectures. Adjacent-Encoder, or AdjEnc, induces competition among documents for topic propagation, and reconstruction among neighbors for semantic capture. Adjacent-Encoder-X, or AdjEnc-X, extends this to also encode the network structure in addition to document content. We evaluate our models on real-world document networks quantitatively and qualitatively, outperforming comparable baselines comprehensively