Harry Potter and the Action Prediction Challenge from Natural Language
Use this link to cite
http://hdl.handle.net/2183/36674Collections
- OpenAIRE [368]
- GI-LYS - Congresos, conferencias, etc. [71]
Metadata
Show full item recordTitle
Harry Potter and the Action Prediction Challenge from Natural LanguageDate
2019-06Citation
David Vilares and Carlos Gómez-Rodríguez. 2019. Harry Potter and the Action Prediction Challenge from Natural Language. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 2124–2130, Minneapolis, Minnesota. Association for Computational Linguistics.
Abstract
[Absctract]: We explore the challenge of action prediction from textual descriptions of scenes, a testbed to approximate whether text inference can be used to predict upcoming actions. As a case of study, we consider the world of the Harry Potter fantasy novels and inferring what spell will be cast next given a fragment of a story. Spells act as keywords that abstract actions (e.g. ‘Alohomora’ to open a door) and denote a response to the environment. This idea is used to automatically build HPAC, a corpus containing 82,836 samples and 85 actions. We then evaluate different baselines. Among the tested models, an LSTM-based approach obtains the best performance for frequent actions and large scene descriptions, but approaches such as logistic regression behave well on infrequent actions.
Keywords
Action prediction
Natural language inference
Textual descriptions
Text-Based Action Prediction in Narrative Text
Natural language inference
Textual descriptions
Text-Based Action Prediction in Narrative Text
Description
The 17th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT 2019) was held in Minneapolis from June 2nd to June 7th, 2019.
Editor version
Rights
Atribución 3.0 España