Papers › Vector of Locally-Aggregated Word Embeddings (VLAWE): A Novel Document-level Representation
Vector of Locally-Aggregated Word Embeddings (VLAWE): A Novel Document-level Representation
Radu Tudor Ionescu, Andrei M. Butnaru
In this paper, we propose a novel representation for text documents based on aggregating word embedding vectors into document embeddings. Our approach is inspired by the Vector of Locally-Aggregated Descriptors used for image representation, and it works as follows. First, the word embeddings gathered from a collection of documents are clustered by k-means in order to learn a codebook of semnatically-related word embeddings. Each word embedding is then associated to its nearest cluster centroid (codeword). The Vector of Locally-Aggregated Word Embeddings (VLAWE) representation of a document is then computed by accumulating the differences between each codeword vector and each word vector (from the document) associated to the respective codeword. We plug the VLAWE representation, which is learned in an unsupervised manner, into a classifier and show that it is useful for a diverse set of text classification tasks. We compare our approach with a broad range of recent state-of-the-art methods, demonstrating the effectiveness of our approach. Furthermore, we obtain a considerable improvement on the Movie Review data set, reporting an accuracy of 93.3%, which represents an absolute gain of 10% over the state-of-the-art approach. Our code is available at https://github.com/raduionescu/vlawe-boswe/.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Document Classification | Reuters-21578 | VLAWE | F1 | 89.3 | #5 of 8 | Archive leaderboard | report |
| Multi-Label Text Classification | Reuters-21578 | VLAWE | Micro-F1 | 89.3 | #7 of 7 | Archive leaderboard | report |
| Sentiment Analysis | MR | VLAWE | Accuracy | 93.3 | #1 of 19 | Archive leaderboard | report |
| Subjectivity Analysis | SUBJ | VLAWE | Accuracy | 95.0 | #6 of 19 | Archive leaderboard | report |
| Text Classification | MR | VLAWE | Accuracy | 93.3 | #1 of 10 | Archive leaderboard | report |
| Text Classification | TREC-6 | VLAWE | Error | 5.8 | #11 of 19 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections