# Contextualizing Citations for Scientific Summarization using Word Embeddings and Domain Knowledge

## TL;DR

This paper introduces an unsupervised model that leverages word embeddings and domain knowledge to better contextualize citations, enhancing scientific summarization accuracy.

## Contribution

The paper presents a novel unsupervised approach combining word embeddings and domain knowledge for contextualizing citations in scientific texts.

## Key findings

- Model significantly outperforms state-of-the-art methods
- Improves citation-based scientific summarization
- Effective use of domain knowledge in citation context extraction

## Abstract

Citation texts are sometimes not very informative or in some cases inaccurate by themselves; they need the appropriate context from the referenced paper to reflect its exact contributions. To address this problem, we propose an unsupervised model that uses distributed representation of words as well as domain knowledge to extract the appropriate context from the reference paper. Evaluation results show the effectiveness of our model by significantly outperforming the state-of-the-art. We furthermore demonstrate how an effective contextualization method results in improving citation-based summarization of the scientific articles.