Exportar Publicação

Ribeiro, E., Mendonça, V., Ribeiro, R., Matos, D. M. De, Sardinha, A., Santos, A. L....Coheur, L. (2019). L2F/INESC-ID at SemEval-2019 Task 2: unsupervised lexical semantic frame induction using contextualized word representations. In Association for Computational Linguistics (Ed.), Proceedings of the 13th International Workshop on Semantic Evaluation. (pp. 130-136). Minneapolis: Association for Computational Linguistics.

E. Ribeiro et al.,  "L2F/INESC-ID at SemEval-2019 Task 2: unsupervised lexical semantic frame induction using contextualized word representations", in Proc. of the 13th Int. Workshop on Semantic Evaluation, Association for Computational Linguistics, Ed., Minneapolis, Association for Computational Linguistics, 2019, pp. 130-136

@inproceedings{ribeiro2019_1714867240442,
	author = "Ribeiro, E. and Mendonça, V. and Ribeiro, R. and Matos, D. M. De and Sardinha, A. and Santos, A. L. and Coheur, L.",
	title = "L2F/INESC-ID at SemEval-2019 Task 2: unsupervised lexical semantic frame induction using contextualized word representations",
	booktitle = "Proceedings of the 13th International Workshop on Semantic Evaluation",
	year = "2019",
	editor = "Association for Computational Linguistics",
	volume = "",
	number = "",
	series = "",
	doi = "10.18653/v1/S19-2019",
	pages = "130-136",
	publisher = "Association for Computational Linguistics",
	address = "Minneapolis",
	organization = "",
	url = "https://www.aclweb.org/anthology/S19-2019"
}

TY  - CPAPER
TI  - L2F/INESC-ID at SemEval-2019 Task 2: unsupervised lexical semantic frame induction using contextualized word representations
T2  - Proceedings of the 13th International Workshop on Semantic Evaluation
AU  - Ribeiro, E.
AU  - Mendonça, V.
AU  - Ribeiro, R.
AU  - Matos, D. M. De
AU  - Sardinha, A.
AU  - Santos, A. L.
AU  - Coheur, L.
PY  - 2019
SP  - 130-136
DO  - 10.18653/v1/S19-2019
CY  - Minneapolis
UR  - https://www.aclweb.org/anthology/S19-2019
AB  - Building large datasets annotated with semantic information, such as FrameNet, is an expensive process. Consequently, such resources are unavailable for many languages and specific domains. This problem can be alleviated by using unsupervised approaches to induce the frames evoked by a collection of documents. That is the objective of the second task of SemEval 2019, which comprises three subtasks: clustering of verbs that evoke the same frame and clustering of arguments into both frame-specific slots and semantic roles. We approach all the subtasks by applying a graph clustering algorithm on contextualized embedding representations of the verbs and arguments. Using such representations is appropriate in the context of this task, since they provide cues for word-sense disambiguation. Thus, they can be used to identify different frames evoked by the same words. Using this approach we were able to outperform all of the baselines reported for the task on the test set in terms of Purity F1, as well as in terms of BCubed F1 in most cases.
ER  -