Abstract
This paper describes the Duluth systems that participated in the Cross–Level Semantic Similarity task of SemEval–2014. These three systems were all unsupervised and relied on a dictionary melded together from various sources, and used first–order (Lesk) and second–order (Vector) overlaps to measure similarity. The first–order overlaps fared well according to Spearman’s correlation (top 5) but less so relative to Pearson’s. Most systems performed at comparable levels for both Spearman’s and Pearson’s measure, which suggests the Duluth approach is potentially unique among the participating systems.
| Original language | English (US) |
|---|---|
| Title of host publication | 8th International Workshop on Semantic Evaluation, SemEval 2014 - co-located with the 25th International Conference on Computational Linguistics, COLING 2014, Proceedings |
| Editors | Preslav Nakov, Torsten Zesch |
| Publisher | Association for Computational Linguistics (ACL) |
| Pages | 247-251 |
| Number of pages | 5 |
| ISBN (Electronic) | 9781941643242 |
| DOIs | |
| State | Published - 2014 |
| Event | 8th International Workshop on Semantic Evaluation, SemEval 2014 - Dublin, Ireland Duration: Aug 23 2014 → Aug 24 2014 |
Publication series
| Name | 8th International Workshop on Semantic Evaluation, SemEval 2014 - co-located with the 25th International Conference on Computational Linguistics, COLING 2014, Proceedings |
|---|
Conference
| Conference | 8th International Workshop on Semantic Evaluation, SemEval 2014 |
|---|---|
| Country/Territory | Ireland |
| City | Dublin |
| Period | 8/23/14 → 8/24/14 |
Bibliographical note
Publisher Copyright:© 8th International Workshop on Semantic Evaluation, SemEval 2014 - co-located with the 25th International Conference on Computational Linguistics, COLING 2014, Proceedings. All rights reserved.