Search Results for author:
Found 2 papers, 2 papers with code
P-SIF: Document Embeddings Using Partition Averaging
One of the key reasons is that a longer document is likely to contain words from many different topics; hence, creating a single vector while ignoring all the topical structure is unlikely to yield an effective document representation.
Improving Document Classification with Multi-Sense Embeddings
Through extensive experiments on multiple real-world datasets, we show that SCDV-MS embeddings outperform previous state-of-the-art embeddings on multi-class and multi-label text categorization tasks.
Ranked #5 on
Document Classification
on Reuters-21578
(F1 metric)
