Better Together: Text + Context
Speaker: Kenneth W Church – Boston, MA, United StatesTopic(s): Artificial Intelligence, Machine Learning, Computer Vision, Natural language processing
Abstract
Graph learning has applications in web search (Page Rank), Product Search (Amazon), Biology, Finance and Traffic Analysis for defense. We will focus on applications in Academic Search because the data is less sensitive and more available. We argue that Content-based filtering (CBF) and Graph-based methods (GB) complement one another. The scientific literature can be viewed as a conversation between authors and the audience. CBF uses abstracts to infer authors' positions, and GB uses citations to infer responses from the audience. In this talk, we describe nine differences between CBF and GB, as well as synergistic opportunities for hybrid combinations. Two embeddings will be used to illustrate these opportunities: (1) Specter, a CBF method based on BERT-like deepnet encodings of abstracts, and (2) ProNE, a GB method based on spectral clustering of more than 200M papers and 2B citations from Semantic Scholar (S2). Resources are available: APIs, a website, and several embeddings of S2 papers.
About this Lecture
Number of Slides: 30Duration: 30 minutes
Languages Available: English
Last Updated:
Request this Lecture
To request this particular lecture, please complete this online form.
Request a Tour
To request a tour with this speaker, please complete this online form.
All requests will be sent to ACM headquarters for review.