# Contextually Propagated Term Weights for Document Representation

## TL;DR

This paper introduces a new method for adjusting term weights in document representations by redistributing weights based on contextual similarity, improving semantic accuracy in unsupervised text classification.

## Contribution

The paper proposes a novel contextually propagated term weighting model that enhances bag-of-words representations by sharing semantic information among similar words.

## Key findings

- Outperforms 8 state-of-the-art baselines in F1 scores
- Effective across datasets of varying difficulty
- Improves semantic coherence in document representations

## Abstract

Word embeddings predict a word from its neighbours by learning small, dense embedding vectors. In practice, this prediction corresponds to a semantic score given to the predicted word (or term weight). We present a novel model that, given a target word, redistributes part of that word's weight (that has been computed with word embeddings) across words occurring in similar contexts as the target word. Thus, our model aims to simulate how semantic meaning is shared by words occurring in similar contexts, which is incorporated into bag-of-words document representations. Experimental evaluation in an unsupervised setting against 8 state of the art baselines shows that our model yields the best micro and macro F1 scores across datasets of increasing difficulty.