Statistical Automatic Summarization in Organic Chemistry

TL;DR

This paper introduces Yachs, a statistical summarizer tailored for organic chemistry documents, demonstrating superior performance over existing methods in automatically generating scientific summaries.

Contribution

The paper presents Yachs, a novel statistical summarization algorithm specifically designed for organic chemistry literature, combining specialized preprocessing with sentence scoring.

Findings

Yachs outperforms other summarizers on organic chemistry articles

Yachs effectively captures key information in scientific documents

The method improves automatic summarization quality in specialized scientific domains

Abstract

We present an oriented numerical summarizer algorithm, applied to producing automatic summaries of scientific documents in Organic Chemistry. We present its implementation named Yachs (Yet Another Chemistry Summarizer) that combines a specific document pre-processing with a sentence scoring method relying on the statistical properties of documents. We show that Yachs achieves the best results among several other summarizers on a corpus of Organic Chemistry articles.