Skip to content


DRAFT: Work in progress

This material is a work in progress, at "rough draft" stage.

– A –

abstractive summarization

– C –

coreference resolution

– D –

deep learning

– E –

eigenvector centrality


entity linking

extractive summarization

– G –

graph algorithms

– L –

language models


lemma graph

– N –

named entity recognition

– P –

personalized pagerank

See the "Personalized PageRank" section in [page1998] for discussion about how to "personalize" the PageRank algorithm, to focus the ranked results within a neighborhood of the graph, given a set of nodes.

Intuitively the E vector corresponds to the distribution of web pages that a random surfer periodically jumps to. As we see below, it can be used to give broad general views of the Web or views which are focused and personalized to a particular individual.

For further discussion, see also [gleich15]:

commonly called personalized PageRank based on the discussion of personalized teleportation behaviors in the original PageRank manuscript (Page, et al., 1999), where the random surfer teleports only to pages that are interesting to the user.

phrase extraction

– S –

semantic relations

stop words

– T –



Last update: 2021-03-25