dc.contributor.author | Marsi, Erwin | |
dc.contributor.author | Skidar, Utpal | |
dc.contributor.author | Marco, Cristina | |
dc.contributor.author | Barik, Biswanath | |
dc.contributor.author | Sætre, Rune | |
dc.date.accessioned | 2017-08-07T07:10:05Z | |
dc.date.available | 2017-08-07T07:10:05Z | |
dc.date.created | 2017-08-04T20:11:09Z | |
dc.date.issued | 2017 | |
dc.identifier.isbn | 978-1-945626-55-5 | |
dc.identifier.uri | http://hdl.handle.net/11250/2449957 | |
dc.description.abstract | We present NTNU’s systems for Task A (prediction of keyphrases) and Task B (labelling as Material, Process or Task) at SemEval 2017 Task 10: Extracting Keyphrases and Relations from Scientific Publications (Augenstein et al., 2017). Our approach relies on supervised machine learning using Conditional Random Fields. Our system yields a micro F-score of 0.34 for Tasks A and B combined on the test data. For Task C (relation extraction), we relied on an independently developed system described in (Barik and Marsi, 2017). For the full Scenario 1 (including relations), our approach reaches a micro F-score of 0.33 (5th place). Here we describe our systems, report results and discuss errors. | nb_NO |
dc.language.iso | eng | nb_NO |
dc.publisher | The Association for Computational Linguistics | nb_NO |
dc.relation.ispartof | 11th International Workshop on Semantic Evaluations (SemEval-2017) | |
dc.relation.uri | http://aclanthology.info/papers/S17-2162/ntnu-1-scienceie-at-semeval-2017-task-10-identifying-and-labelling-keyphrases-with-conditional-random-fields | |
dc.title | NTNU-1@ScienceIE at SemEval-2017 Task 10: Identifying and Labelling Keyphrases with Conditional Random Fields | nb_NO |
dc.type | Chapter | nb_NO |
dc.description.version | submittedVersion | nb_NO |
dc.source.pagenumber | 938-941 | nb_NO |
dc.identifier.cristin | 1484311 | |
dc.relation.project | Norges teknisk-naturvitenskapelige universitet: 69310260 | nb_NO |
dc.description.localcode | This is the authors' manuscript to the article (preprint). | nb_NO |
cristin.unitcode | 194,63,10,0 | |
cristin.unitcode | 194,18,21,70 | |
cristin.unitname | Institutt for datateknikk og informasjonsvitenskap | |
cristin.unitname | Norwegian Media Technology Lab | |
cristin.ispublished | true | |
cristin.fulltext | preprint | |
cristin.qualitycode | 1 | |