Vilares, DavidGómez-Rodríguez, Carlos2024-05-282024-05-282019-06David 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.http://hdl.handle.net/2183/36674The 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.[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.engAtribución 3.0 Españahttp://creativecommons.org/licenses/by/3.0/es/Action predictionNatural language inferenceTextual descriptionsText-Based Action Prediction in Narrative Textconference outputopen access