SciEv: Finding Scientific Evidence Papers for Scientific News

TL;DR

SciEv is an automated system designed to find scientific papers that serve as evidence for scientific news articles, improving citation accuracy and reducing manual effort by leveraging domain knowledge entities and advanced document representations.

Contribution

The paper introduces SciEv, a novel two-stage system utilizing domain knowledge entities and transformer models for effective scientific evidence retrieval from news articles.

Findings

Transformer models excel in DKE extraction.

TFIDF-based representations achieve high precision in reranking.

System attains up to 74% precision at top 10 results.

Abstract

In the past decade, many scientific news media that report scientific breakthroughs and discoveries emerged, bringing science and technology closer to the general public. However, not all scientific news article cites proper sources, such as original scientific papers. A portion of scientific news articles contain misinterpreted, exaggerated, or distorted information that deviates from facts asserted in the original papers. Manually identifying proper citations is laborious and costly. Therefore, it is necessary to automatically search for pertinent scientific papers that could be used as evidence for a given piece of scientific news. We propose a system called SciEv that searches for scientific evidence papers given a scientific news article. The system employs a 2-stage query paradigm with the first stage retrieving candidate papers and the second stage reranking them. The key feature of SciEv is it uses domain knowledge entities (DKEs) to find candidates in the first stage, which proved to be more effective than regular keyphrases. In the reranking stage, we explore different document representations for news articles and candidate papers. To evaluate our system, we compiled a pilot dataset consisting of 100 manually curated (news,paper) pairs from ScienceAlert and similar websites. To our best knowledge, this is the first dataset of this kind. Our experiments indicate that the transformer model performs the best for DKE extraction. The system achieves a P@1=50%, P@5=71%, and P@10=74% when it uses a TFIDF-based text representation. The transformer-based re-ranker achieves a comparable performance but costs twice as much time. We will collect more data and test the system for user experience.