摘要
We consider open domain event extraction, the task of extracting unconstraint types of events from news clusters. A novel latent variable neural model is constructed, which is scalable to very large corpus. A dataset is collected and manually annotated, with task-specific evaluation metrics being designed. Results show that the proposed unsupervised model gives better performance compared to the state-of-the-art method for event schema induction.
| 源语言 | 英语 |
|---|---|
| 主期刊名 | ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference |
| 出版商 | Association for Computational Linguistics (ACL) |
| 页 | 2860-2871 |
| 页数 | 12 |
| ISBN（电子版） | 9781950737482 |
| 出版状态 | 已出版 - 2020 |
| 活动 | 57th Annual Meeting of the Association for Computational Linguistics, ACL 2019 - Florence, 意大利 期限: 28 7月 2019 → 2 8月 2019 |
出版系列
| 姓名 | ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference |
|---|
会议
| 会议 | 57th Annual Meeting of the Association for Computational Linguistics, ACL 2019 |
|---|---|
| 国家/地区 | 意大利 |
| 市 | Florence |
| 时期 | 28/07/19 → 2/08/19 |
指纹
探究 'Open domain event extraction using neural latent variable models' 的科研主题。它们共同构成独一无二的指纹。引用此
Liu, X., Huang, H., & Zhang, Y. (2020). Open domain event extraction using neural latent variable models. 在 ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (页码 2860-2871). (ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference). Association for Computational Linguistics (ACL).