![Best apple laptop for college students 2016](https://cdn1.cdnme.se/5447227/9-3/24_64e61dfd9606ee7f8b257167.png)
![endnote umd download endnote umd download](https://aclanthology.org/thumb/W14-2106.jpg)
Association for Computational Linguistics. In Proceedings of the 12th International Workshop on Semantic Evaluation, pages 1022–1026, New Orleans, Louisiana. UMD at SemEval-2018 Task 10: Can Word Embeddings Capture Discriminative Attributes?. SIGLEX Publisher: Association for Computational Linguistics Note: Pages: 1022–1026 Language: URL: DOI: 10.18653/v1/S18-1170 Bibkey: zhang-carpuat-2018-umd Cite (ACL): Alexander Zhang and Marine Carpuat.
![endnote umd download endnote umd download](https://aclanthology.org/thumb/W14-2708.jpg)
Anthology ID: S18-1170 Volume: Proceedings of the 12th International Workshop on Semantic Evaluation Month: June Year: 2018 Address: New Orleans, Louisiana Venue: SemEval SIGs: SIGSEM We also show that cosine similarity features are more effective, both in unsupervised systems (F-score of 65%) and supervised systems (F-score of 67%).
![endnote umd download endnote umd download](https://aclanthology.org/thumb/W14-1701.jpg)
Using a gaussian SVM model trained only on validation data results in an F-score of 60%. Our submission casts this problem as supervised binary classification using only word embedding features. Our study aims to determine whether word embeddings can address this challenging task. Abstract We describe the University of Maryland’s submission to SemEval-018 Task 10, “Capturing Discriminative Attributes”: given word triples (w1, w2, d), the goal is to determine whether d is a discriminating attribute belonging to w1 but not w2.
![Best apple laptop for college students 2016](https://cdn1.cdnme.se/5447227/9-3/24_64e61dfd9606ee7f8b257167.png)