Mimicking Human Process: Text Representation via Latent Semantic Clustering for Classification
This is an incremental improvement for text classification tasks, offering a method to enhance semantic expression in text representation.
The paper tackles the problem of text classification by proposing a new representation scheme that clusters words by latent semantics and concatenates cluster vectors, achieving effectiveness on five benchmarks.
Considering that words with different characteristic in the text have different importance for classification, grouping them together separately can strengthen the semantic expression of each part. Thus we propose a new text representation scheme by clustering words according to their latent semantics and composing them together to get a set of cluster vectors, which are then concatenated as the final text representation. Evaluation on five classification benchmarks proves the effectiveness of our method. We further conduct visualization analysis showing statistical clustering results and verifying the validity of our motivation.