Document Network Projection in Pretrained Word Embedding Space
This is an incremental improvement for information retrieval tasks like recommendation and classification in document networks.
The paper tackles the problem of projecting linked documents into a pretrained word embedding space by introducing Regularized Linear Embedding (RLE), which leverages both textual content and network similarities. The result shows that RLE outperforms or matches existing methods on node classification and link prediction tasks.
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. In addition to the textual content, we leverage a matrix of pairwise similarities providing complementary information (e.g., the network proximity of two documents in a citation graph). We first build a simple word vector average for each document, and we use the similarities to alter this average representation. The document representations can help to solve many information retrieval tasks, such as recommendation, classification and clustering. We demonstrate that our approach outperforms or matches existing document network embedding methods on node classification and link prediction tasks. Furthermore, we show that it helps identifying relevant keywords to describe document classes.