--- title: "Event Detection Using Frame-Semantic — Spiliopoulou 2017" description: "The paper addresses event nugget detection and type/subtype classification under the ACE 2005 scheme." authors: ["Evangelia Spiliopoulou", "Eduard Hovy", "Teruko Mitamura"] year: 2017 venue: "Proceedings of the Events and Stories in the News Workshop" source: "https://aclanthology.org/W17-2703/" doi: "10.18653/v1/w17-2703" licence: "CC BY 4.0 (ACL Anthology)" licence_url: "https://creativecommons.org/licenses/by/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/papers/spiliopoulou-2017-event-detection-frame-semantic-parser/" --- [Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/spiliopoulou-2017-event-detection-frame-semantic-parser/) [home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2017](https://md.research.elamur.ai/free/papers/2017/page/2/) / Event Detection Using Frame-Semantic Parser # Event Detection Using Frame-Semantic Parser **Authors:** Evangelia Spiliopoulou, [Eduard Hovy](https://md.research.elamur.ai/free/authors/eduard-hovy/), [Teruko Mitamura](https://md.research.elamur.ai/free/authors/teruko-mitamura/) · **Year:** 2017 · **Venue:** Proceedings of the Events and Stories in the News Workshop · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/) **Links:** [Publisher's page](https://aclanthology.org/W17-2703/) · [PDF](https://aclanthology.org/W17-2703.pdf) · [DOI 10.18653/v1/w17-2703](https://doi.org/10.18653/v1/w17-2703) · [OpenAlex](https://openalex.org/W2741822233) **Citations:** 11 citations (openalex-snapshot · 2026-10-14) · 6 in our library, of the 140673 papers whose bibliographies we read ## Summary The paper addresses event nugget detection and type/subtype classification under the ACE 2005 scheme. The authors argue that deep learning detectors built on shallow lexical cues and embeddings tend to be precise but miss many events. Their alternative trades precision for coverage. The frame-semantic parser Semafor proposes candidate triggers with their FrameNet frames and Frame Elements. Stanford CoreNLP POS tags split the candidates into verbal and nominal ones. The authors manually built correspondences linking FrameNet frames to ACE event types and subtypes, with separate tables for verbs and nouns plus a few lexical disambiguation rules, and only candidates whose frame matches an ACE event are retained. The method needs no training, so it was evaluated on all 106 ACE 2005 Newswire articles. It reached higher recall than the compared state-of-the-art systems but much lower precision. In a preliminary experiment, re-classifying its candidates with simple learned models raised F1. The authors conclude that high-recall semantic candidate generation is a useful front end for learned classifiers. ## Key points - **Raw parser baseline:** Semafor alone on ACE Newswire found 82.53% of events, but precision was only 6.8% (F1 12.6). The FrameNet→ACE filter is therefore essential. - **Event Nugget Detection:** The system scored R 72.6 / P 43.3 / F1 54.2, identifying 1131 of 1557 mentions. For comparison, DMCNN scored R 67.7 / F1 73.5 and MSEP scored R 69.8 / F1 72.6. - **Classification of found events:** 1044 types and 1018 subtypes were correct. This means about 92.3% and 90.0% of correctly detected nuggets also received the right type and subtype. Subtype classification overall scored R 65.4 / P 39.0 / F1 48.35. - **Hybrid experiment:** The data used a 60/40 split, with features including the lexical context, frame, Frame Elements, and predicted type. A Random Forest raised F1 from 51.11 to 61.1 (P 72.6, R 52.8). A vanilla Neural Net reached F1 57.49, which the authors attribute to the small dataset of about 1550 training instances. - **Resources:** The work uses FrameNet (over 1,200 frames), the Semafor parser, Stanford CoreNLP, and the ACE 2005 ontology (8 types, 33 subtypes). *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* Fields: [Linguistics & languages](https://md.research.elamur.ai/free/shelves/linguistics/) Topics: [Semantic role labeling](https://md.research.elamur.ai/free/topics/semantic-role-labeling/) ## Cite The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{spiliopoulou2017event, title = {{Event Detection Using Frame-Semantic Parser}}, author = {Spiliopoulou, Evangelia and Hovy, Eduard and Mitamura, Teruko}, booktitle = {Proceedings of the Events and Stories in the News Workshop}, year = {2017}, doi = {10.18653/v1/w17-2703}, url = {https://doi.org/10.18653/v1/w17-2703} } ``` - [← previous Event Coreference Resolution by Iteratively Unfolding Inter-dependencies among Events](https://md.research.elamur.ai/free/papers/choubey-2017-event-coreference-resolution-iteratively-unfolding/) - [next → Examples and Specifications that Prove a Point: Identifying Elaborative and Argumentative Discourse Relations](https://md.research.elamur.ai/free/papers/scholman-2017-examples-specifications-that-prove-point/) - [↑ back to papers of 2017](https://md.research.elamur.ai/free/papers/2017/page/2/) ## References 8 references, 5 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Collin F. Baker, Charles J. Fillmore, and John B. Lowe. 1998. The berkeley framenet project. In Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics -Volume 1. [find](https://scholar.google.com/scholar?q=Collin+F%2E+Baker%2C+Charles+J%2E+Fillmore%2C+and+John+B%2E+Lowe%2E+1998%2E+The+berkeley+framenet+project%2E+In+Proceedings+of+the+36th+Annual+Meeting+of+the+Association+for+Computational+Linguistics+and+17th+Interna) [our card](https://md.research.elamur.ai/free/papers/lex-1998-baker-berkeley-framenet/) 2. Yubo Chen, Liheng Xu, Kang Liu, Daojian Zeng, and Jun Zhao. 2015. Event extraction via dynamic multi-pooling convolutional neural networks. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Proces… [find](https://scholar.google.com/scholar?q=Yubo+Chen%2C+Liheng+Xu%2C+Kang+Liu%2C+Daojian+Zeng%2C+and+Jun+Zhao%2E+2015%2E+Event+extraction+via+dynamic+multi%2Dpooling+convolutional+neural+networks%2E+In+Proceedings+of+the+53rd+Annual+Meeting+of+the+Association) 3. Dipanjan Das, Desai Chen, André FT Martins, Nathan Schneider, and Noah A Smith. 2014. Frame-semantic parsing. Computational Linguistics . [find](https://scholar.google.com/scholar?q=Dipanjan+Das%2C+Desai+Chen%2C+Andre%CC%81+FT+Martins%2C+Nathan+Schneider%2C+and+Noah+A+Smith%2E+2014%2E+Frame%2Dsemantic+parsing%2E+Computational+Linguistics+%2E) [our card](https://md.research.elamur.ai/free/papers/das-2014-frame-semantic-parsing/) 4. Reza Ghaeini, Xiaoli Z Fern, Liang Huang, and Prasad Tadepalli. 2016. Event nugget detection with forward-backward recurrent neural networks. In The 54th Annual Meeting of the Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Reza+Ghaeini%2C+Xiaoli+Z+Fern%2C+Liang+Huang%2C+and+Prasad+Tadepalli%2E+2016%2E+Event+nugget+detection+with+forward%2Dbackward+recurrent+neural+networks%2E+In+The+54th+Annual+Meeting+of+the+Association+for+Computat) 5. Shulin Liu, Yubo Chen, Shizhu He, Kang Liu, and Jun Zhao. 2016. Leveraging framenet to improve automatic event detection. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016, August 7-12, 2016, Berlin, Germany, Volume 1: Long Papers. [find](https://scholar.google.com/scholar?q=Shulin+Liu%2C+Yubo+Chen%2C+Shizhu+He%2C+Kang+Liu%2C+and+Jun+Zhao%2E+2016%2E+Leveraging+framenet+to+improve+automatic+event+detection%2E+In+Proceedings+of+the+54th+Annual+Meeting+of+the+Association+for+Computational) [our card](https://md.research.elamur.ai/free/papers/liu-2016-leveraging-framenet-improve-automatic-event/) 6. Christopher D. Manning, Mihai Surdeanu, John Bauer, Jenny Finkel, Steven J. Bethard, and David Mc-Closky. 2014. The Stanford CoreNLP natural language processing toolkit. In Association for Computational Linguistics (ACL) System Demonstrations. [find](https://scholar.google.com/scholar?q=Christopher+D%2E+Manning%2C+Mihai+Surdeanu%2C+John+Bauer%2C+Jenny+Finkel%2C+Steven+J%2E+Bethard%2C+and+David+Mc%2DClosky%2E+2014%2E+The+Stanford+CoreNLP+natural+language+processing+toolkit%2E+In+Association+for+Computation) [our card](https://md.research.elamur.ai/free/papers/manning-2014-stanford-corenlp-natural-language-processing/) 7. Thien Huu Nguyen and Ralph Grishman. 2015. Event detection and domain adaptation with convolutional neural networks. In ACL (2). [find](https://scholar.google.com/scholar?q=Thien+Huu+Nguyen+and+Ralph+Grishman%2E+2015%2E+Event+detection+and+domain+adaptation+with+convolutional+neural+networks%2E+In+ACL+%282%29%2E) 8. Haoruo Peng, Yangqiu Song, and Dan Roth. 2016. Event detection and co-reference with minimal supervision. In EMNLP. [find](https://scholar.google.com/scholar?q=Haoruo+Peng%2C+Yangqiu+Song%2C+and+Dan+Roth%2E+2016%2E+Event+detection+and+co%2Dreference+with+minimal+supervision%2E+In+EMNLP%2E) [our card](https://md.research.elamur.ai/free/papers/peng-2016-event-detection-co-reference-minimal/)