UNPMC: Naive Approach to Extract Keyphrases from Scientific Articles

Proceedings of the 5th International Workshop on Semantic Evaluation, ACL 2010, pages 178–181, Uppsala, Sweden, 15-16 July 2010. c⃝2010 Association for Computational Linguistics UNPMC: Na¨ıve Approach to Extract Keyphrases from Scientific Articles Jungyeul Park LINA, Universit´e de Nantes Nantes, France jungyeul.park @univ-nantes.fr Jong Gun Lee LIP6-CNRS, UPMC (Paris 6) Paris, France jonggun.lee @lip6.fr B´eatrice Daille LINA, Universit´e de Nantes Nantes, France beatrice.daille @univ-nantes.fr Abstract We describe our method for extracting keyphrases from scientific articles which we participate in the shared task of SemEval-2 Evaluation Exercise. Even though general-purpose term extractors along with linguistically-motivated analy- sis allow us to extract elaborated morpho- syntactic variation forms of terms, a na¨ıve statistic approach proposed in this paper is very simple and quite efficient for ex- tracting keyphrases especially from well- structured scientific articles. Based on the characteristics of keyphrases with sec- tion information, we obtain 18.34% for f-measure using top 15 candidates. We also show further improvement without any complications and we discuss this at the end of the paper. 1 Introduction1 Key phrases are a set of words to capture the main topic of the document. Since key phrases con- tain the substance of the document, they are used in the large spectrum of areas; from applications which explicitly use key phrases such as automatic indexing, documents classification and search en- gine optimization in information retrieval, to ap- plications which implicitly use key phrases such as summarization and question-answering systems. During the last decade, many previous works have dealt with the various methods for automatically extracting key phrases (e.g., Frank et al., 1999; Barker and Corrnacchia, 2000; Turney, 2003; Medelyan and Witten, 2006; Nguyen and Kan, 2007; Wan and Xiao, 2008). 1UNPMC means the collaborative team from Laboratoire d’Informatique de Nantes Atlantique of the Universit´e de Nantes and Laboratoire d’Informatique de Paris 6 of the Uni- versit´e Pierre et Marie Curie. The task of extracting key phrases would be considered as a subtask of extracting terminology if key phrases are a kind of terms. Typical ap- proaches for automatically extracting terms use linguistic preprocessing which involves morpho- syntactic analysis such as part-of-speech tagging and phrase chunking, and statistical postprocess- ing such as log likelihood which compares the term frequencies in a document against their ex- pected frequencies derived in a bigger text. Be- sides, extracting terms prefers syntactically plau- sible noun phrases (NPs) which are mainly multi- words terms. Kim and Kan (2009) report that most of key phrases are often simple words than less of- ten compound words2. The task for extracting key phrases tend to in- clude analyzing the document structure. Espe- cially, extracting key phrases from well-structured scientific articles should consider cross-section in- formation (Nguyen and Kan, 2007). This informa- tion has been explored to assess the suitability of features during learning in Kim and Kan (2009). Extracting key phrases, however, is more than to extracting terminology or analyzing the document structure. While terms are words which appear in specific contexts and analyse concept structures in domains of human …

Content truncated to 500 words