This paper describes the Duluth systems that participated in Task 15 of SemEval 2015. The goal of the task was to automatically construct dictionary entries (via a series of three subtasks). Our systems participated in subtask 2, which involved automatically clustering the contexts in which a target word occurs into its different senses. Our results are consistent with previous word sense induction and discrimination findings, where it proves difficult to beat a baseline algorithm that assigns all instances of a target word to a single sense. However, our method of predicting the number of senses automatically fared quite well.
|Original language||English (US)|
|Title of host publication||SemEval 2015 - 9th International Workshop on Semantic Evaluation, co-located with the 2015 Conference of the North American Chapter of the Association for Computational Linguistics|
|Subtitle of host publication||Human Language Technologies, NAACL-HLT 2015 - Proceedings|
|Editors||Preslav Nakov, Torsten Zesch, Daniel Cer, David Jurgens|
|Publisher||Association for Computational Linguistics (ACL)|
|Number of pages||5|
|State||Published - 2015|
|Event||9th International Workshop on Semantic Evaluation, SemEval 2015 - Denver, United States|
Duration: Jun 4 2015 → Jun 5 2015
|Name||SemEval 2015 - 9th International Workshop on Semantic Evaluation, co-located with the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2015 - Proceedings|
|Conference||9th International Workshop on Semantic Evaluation, SemEval 2015|
|Period||6/4/15 → 6/5/15|
Bibliographical noteFunding Information:
I would like to thank Bridget McInnes for her help in understanding the task, and for very useful brainstorming discussions.
© 2015 Association for Computational Linguistics