HUMB: Automatic Key Term Extraction from Scientific Articles in GROBID

Proceedings of the 5th International Workshop on Semantic Evaluation, ACL 2010, pages 248–251, Uppsala, Sweden, 15-16 July 2010. c⃝2010 Association for Computational Linguistics HUMB: Automatic Key Term Extraction from Scientific Articles in GROBID Patrice Lopez INRIA Berlin, Germany patrice lopez@hotmail.com Laurent Romary INRIA & HUB-IDSL Berlin, Germany laurent.romary@inria.fr Abstract The Semeval task 5 was an opportunity for experimenting with the key term ex- traction module of GROBID, a system for extracting and generating bibliographical information from technical and scientific documents. The tool first uses GROBID’s facilities for analyzing the structure of sci- entific articles, resulting in a first set of structural features. A second set of fea- tures captures content properties based on phraseness, informativeness and keyword- ness measures. Two knowledge bases, GRISP and Wikipedia, are then exploited for producing a last set of lexical/semantic features. Bagged decision trees appeared to be the most efficient machine learning algorithm for generating a list of ranked key term candidates. Finally a post rank- ing was realized based on statistics of co- usage of keywords in HAL, a large Open Access publication repository. 1 Introduction Key terms (or keyphrases or keywords) are meta- data providing general information about the con- tent of a document. Their selection by authors or readers is, to a large extent, subjective which makes automatic extraction difficult. This is, how- ever, a valuable exercise, because such key terms constitute good topic descriptions of documents which can be used in particular for information retrieval, automatic document clustering and clas- sification. Used as subject headings, better key- words can lead to higher retrieval rates of an arti- cle in a digital library. We view automatic key term extraction as a sub- task of the general problem of extraction of tech- nical terms which is crucial in technical and scien- tific documents (Ahmad and Collingham, 1996). Among the extracted terms for a given scientific document in a given collection, which key terms best characterize this document? This article describes the system realized for the Semeval 2010 task 5, based on GROBID’s (GeneRation Of BIbilographic Data) module ded- icated to key term extraction. GROBID is a tool for analyzing technical and scientific documents, focusing on automatic bibliographical data extrac- tion (header, citations, etc.) (Lopez, 2009) and structure recognition (section titles, figures, etc). As the space for the system description is very limited, this presentation focuses on key aspects. We present first an overview of our approach, then our selection of features (section 3), the different tested machine learning models (section 4) and the final post-ranking (section 5). We briefly describe our unsuccessful experiments (section 6) and we conclude by discussing future works. 2 Bases Principle As most of the successful works for keyphrase extraction, our approach relies on Ma- chine Learning (ML). The following steps are ap- plied to each document to be processed: 1. Analysis of the structure of the article. 2. Selection of candidate terms. 3. Calculation of features. 4. Application of a ML model for evaluating each candidate term independently. …

Content truncated to 500 words