# Redefining Context Windows for Word Embedding Models: An Experimental Study

arXiv: https://arxiv.org/abs/1704.05781 · HTML: https://mlsanity.com/paper/1704.05781/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Apr 2017.

## Built on by (most cited first, 3 of 3)

- [Fusing Domain-Specific Content from Large Language Models into Knowledge Graphs for Enhanced Zero Shot Object State Classification](https://mlsanity.com/paper/2403.12151/) (2024)
- [A methodology to characterize bias and harmful stereotypes in natural language processing in Latin America](https://mlsanity.com/paper/2207.06591/) (2022)
- [DataSculpt: Crafting Data Landscapes for Long-Context LLMs through Multi-Objective Partitioning](https://mlsanity.com/paper/2409.00997/) (2024)

## Abstract (arXiv)

Distributional semantic models learn vector representations of words through the contexts they occur in. Although the choice of context (which often takes the form of a sliding window) has a direct influence on the resulting embeddings, the exact role of this model component is still not fully understood. This paper presents a systematic analysis of context windows based on a set of four distinct hyper-parameters. We train continuous Skip-Gram models on two English-language corpora for various combinations of these hyper-parameters, and evaluate them on both lexical similarity and analogy tasks. Notable experimental results are the positive impact of cross-sentential contexts and the surprisingly good performance of right-context windows.