Search Results for author:
Found 9 papers, 5 papers with code
Anchor Prediction: A Topic Modeling Approach
We propose a contextualized relational topic model, CRTM, that models directed links between documents as a function of the local context of the anchor in the source document and the whole content of the target document.
New Datasets and a Benchmark of Document Network Embedding Methods for Scientific Expert Finding
In this direction, document network embedding methods seem to be an ideal choice for building representations of the scientific literature.
Document Network Projection in Pretrained Word Embedding Space
We present Regularized Linear Embedding (RLE), a novel method that projects a collection of linked documents (e. g. citation network) into a pretrained word embedding space.
Inductive Document Network Embedding with Topic-Word Attention
We train these word and topic vectors through our general model, Inductive Document Network Embedding (IDNE), by leveraging the connections in the document network.
Document Network Embedding: Coping for Missing Content and Missing Links
Searching through networks of documents is an important task.
Link Prediction with Mutual Attention for Text-Attributed Networks
In this extended abstract, we present an algorithm that learns a similarity measure between documents from the network topology of a structured corpus.
Global Vectors for Node Representations
Even though SGNS better handles non co-occurrence than GloVe, it has a worse time-complexity.
Event detection, tracking, and visualization in Twitter: a mention-anomaly-based approach
In this paper we propose MABED (i. e. mention-anomaly-based event detection), a novel statistical method that relies solely on tweets and leverages the creation frequency of dynamic links (i. e. mentions) that users insert in tweets to detect significant events and estimate the magnitude of their impact over the crowd.
Social and Information Networks
CommentWatcher: An Open Source Web-based platform for analyzing discussions on web forums
Constructed as a web platform, CommentWatcher features automatic mass fetching of user posts from forum on multiple sites, extracting topics, visualizing the topics as an expression cloud and exploring their temporal evolution.
