While existing approaches for these tasks assume accurate knowledge of the document date, this is not always available, especially for arbitrary documents from the Web.Document Dating is a challenging problem which requires inference over the temporal structure of the document.Graph matching problems generally consist of making connections within graphs using edges that do not share common vertices, such as pairing students in a class according to their respective qualifications; or it may consist of creating a bipartite matching, where two subsets of vertices are distinguished and each vertex in one subgroup must be matched to a vertex in another subgroup.Bipartite matching is used, for example, to match men and women on a dating site.In max-flow problems, like in matching problems, augmenting paths are paths where the amount of flow between the source and sink can be increased.The majority of realistic matching problems are much more complex than those presented above.
Graph matching problems are very common in daily activities.
Source: Bulletin on Retirement and Disability Bulletin on Health including Archive of Lists of Affiliates' Work in Medical and Other Journals with Pre-Publication Restrictions Archives of Bulletin on Aging and Health Digest — Non-technical summaries of 4-8 working papers per month Reporter — News about the Bureau and its activities.
Document date is essential for many important tasks, such as document retrieval, summarization, event detection, etc.
Prior document dating systems have largely relied on handcrafted features while ignoring such document internal structures.
In this paper, we propose Neural Dater, a Graph Convolutional Network (GCN) based document dating approach which jointly exploits syntactic and temporal graph structures of document in a principled way.
This added complexity often stems from graph labeling, where edges or vertices labeled with quantitative attributes, such as weights, costs, preferences or any other specifications, which adds constraints to potential matches.