Contextualizing Citations for Scientific Summarization using Word Embeddings and Domain Knowledge
This addresses the issue of unreliable citations for researchers and summarization systems, though it appears incremental as it builds on existing word embedding and domain knowledge techniques.
The paper tackled the problem of uninformative or inaccurate citation texts by proposing an unsupervised model that uses word embeddings and domain knowledge to extract appropriate context from referenced papers, resulting in significantly outperforming state-of-the-art methods and improving citation-based summarization.
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.