Are Abstracts Enough for Hypothesis Generation?

TL;DR

This study evaluates whether abstracts alone suffice for hypothesis generation or if full-text papers improve results, analyzing the trade-offs between data source length, quality, and computational cost in knowledge network-based systems.

Contribution

It systematically compares the impact of abstract versus full-text corpora on hypothesis generation quality and interpretability, highlighting the importance of document length over quantity.

Findings

Longer documents slightly improve result quality

Full-text papers introduce more intruder terms, reducing interpretability

Document length impacts results more than document count

Abstract

The potential for automatic hypothesis generation (HG) systems to improve research productivity keeps pace with the growing set of publicly available scientific information. But as data becomes easier to acquire, we must understand the effect different textual data sources have on our resulting hypotheses. Are abstracts enough for HG, or does it need full-text papers? How many papers does an HG system need to make valuable predictions? How sensitive is a general-purpose HG system to hyperparameter values or input quality? What effect does corpus size and document length have on HG results? To answer these questions we train multiple versions of knowledge network-based HG system, Moliere, on varying corpora in order to compare challenges and trade offs in terms of result quality and computational requirements. Moliere generalizes main principles of similar knowledge network-based HG systems and reinforces them with topic modeling components. The corpora include the abstract and full-text versions of PubMed Central, as well as iterative halves of MEDLINE, which allows us to compare the effect document length and count has on the results. We find that, quantitatively, corpora with a higher median document length result in marginally higher quality results, yet require substantially longer to process. However, qualitatively, full-length papers introduce a significant number of intruder terms to the resulting topics, which decreases human interpretability. Additionally, we find that the effect of document length is greater than that of document count, even if both sets contain only paper abstracts. Reproducibility: Our code and data are available at github.com/jsybran/moliere, and bit.ly/2GxghpM respectively.