SemRe-Rank: Improving Automatic Term Extraction By Incorporating Semantic Relatedness With Personalised PageRank

TL;DR

SemRe-Rank enhances existing automatic term extraction methods by integrating semantic relatedness through personalized PageRank, significantly improving their accuracy across diverse datasets and base algorithms.

Contribution

This paper introduces SemRe-Rank, a novel approach that incorporates semantic relatedness into ATE by using word embeddings and personalized PageRank to improve term extraction performance.

Findings

Achieved up to 15% improvement in Precision at top K

Achieved up to 28% improvement in F1 score

Outperformed TextRank-based approach by up to 8 points in Precision

Abstract

Automatic Term Extraction deals with the extraction of terminology from a domain specific corpus, and has long been an established research area in data and knowledge acquisition. ATE remains a challenging task as it is known that there is no existing ATE methods that can consistently outperform others in any domain. This work adopts a refreshed perspective to this problem: instead of searching for such a 'one-size-fit-all' solution that may never exist, we propose to develop generic methods to 'enhance' existing ATE methods. We introduce SemRe-Rank, the first method based on this principle, to incorporate semantic relatedness - an often overlooked venue - into an existing ATE method to further improve its performance. SemRe-Rank incorporates word embeddings into a personalised PageRank process to compute 'semantic importance' scores for candidate terms from a graph of semantically related words (nodes), which are then used to revise the scores of candidate terms computed by a base ATE algorithm. Extensively evaluated with 13 state-of-the-art base ATE methods on four datasets of diverse nature, it is shown to have achieved widespread improvement over all base methods and across all datasets, with up to 15 percentage points when measured by the Precision in the top ranked K candidate terms (the average for a set of K's), or up to 28 percentage points in F1 measured at a K that equals to the expected real terms in the candidates (F1 in short). Compared to an alternative approach built on the well-known TextRank algorithm, SemRe-Rank can potentially outperform by up to 8 points in Precision at top K, or up to 17 points in F1.