DERIUNLP: A Context Based Approach to Automatic Keyphrase Extraction

Proceedings of the 5th International Workshop on Semantic Evaluation, ACL 2010, pages 146–149, Uppsala, Sweden, 15-16 July 2010. c⃝2010 Association for Computational Linguistics DERIUNLP: A Context Based Approach to Automatic Keyphrase Extraction Georgeta Bordea Unit for Natural Language Processing Digital Enterprise Research Institute National University of Ireland, Galway georgeta.bordea@deri.org Paul Buitelaar Unit for Natural Language Processing Digital Enterprise Research Institute National University of Ireland, Galway paul.buitelaar@deri.org Abstract The DERI UNLP team participated in the SemEval 2010 Task #5 with an unsuper- vised system that automatically extracts keyphrases from scientific articles. Our approach does not only consider a general description of a term to select keyphrase candidates but also context information in the form of “skill types”. Even though our system analyses only a limited set of candidates, it is still able to outperform baseline unsupervised and supervised ap- proaches. 1 Introduction Keyphrases provide users overwhelmed by the richness of information currently available with useful insight into document content but at the same time they are a valuable input for a variety of NLP applications such as summarization, cluster- ing and searching. The SemEval 2010 competition included a task targeting the Automatic Keyphrase Extraction from Scientific Articles (Kim et al., 2010). Given a set of scientific articles partic- ipants are required to assign to each document keyphrases extracted from text. We participated in this task with an unsuper- vised approach for keyphrase extraction that does not only consider a general description of a term to select candidates but also takes into consider- ation context information. The larger context of our work is the extraction of expertise topics for Expertise Mining (Bordea, 2010). Expertise Mining is the task of automatically extracting expertise topics and expertise profiles from a collection of documents. Even though the Expertise Mining task and the Keyphrase Extrac- tion task are essentially different, it is important to assess the keyphraseness of extracted expertise topics, i.e., their ability to represent the content of a document. Here we will report only relevant findings for the Keyphrase Extraction task, focus- ing on the overlapping aspects of the two afore- mentioned tasks. After giving an overview of related work in sec- tion 2 we introduce skill types and present our can- didate selection method in section 3. Section 4 de- scribes the features used for ranking and filtering the candidate keyphrases and Section 5 presents our results before we conclude in Section 6. 2 Related Work The current methods for keyphrase extraction can be categorized in supervised and unsupervised ap- proaches. Typically any keyphrase extraction sys- tem works in two stages. In the first stage a gen- eral set of candidates is selected by extracting the tokens of a text. In the second stage unsupervised approaches combine a set of features in a rank to select the most important keyphrases and super- vised approaches use a training corpus to learn a keyphrase extraction model. Mihalcea and Tarau (2004) propose an unsuper- vised approach that considers single tokens as ver- tices of a graph …

Content truncated to 500 words