SemRe-Rank: Improving Automatic Term Extraction By Incorporating Semantic Relatedness With Personalised PageRank
| Autor: | Jie Gao, Fabio Ciravegna, Ziqi Zhang |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
FOS: Computer and information sciences
Word embedding General Computer Science Computer science text mining 02 engineering and technology computer.software_genre Machine learning Terminology law.invention Computer Science - Information Retrieval Semantic similarity PageRank law 020204 information systems 0202 electrical engineering electronic engineering information engineering termhood information extraction information retrieval Automatic term extraction ATE automatic term recognition ATR personalised pagerank word embedding semantic relatedness Computer Science - Computation and Language business.industry Percentage point Knowledge acquisition Information extraction Graph (abstract data type) 020201 artificial intelligence & image processing Artificial intelligence business computer Computation and Language (cs.CL) Information Retrieval (cs.IR) |
| ISSN: | 1556-4681 |
| DOI: | 10.48550/arxiv.1711.03373 |
| Popis: | 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. Comment: Accepted by ACM TKDD. This is a pre-print |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|