Abstract
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.- Anthology ID:
- N19-1218
- Volume:
- 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)
- Month:
- June
- Year:
- 2019
- Address:
- Minneapolis, Minnesota
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2124–2130
- Language:
- URL:
- https://aclanthology.org/N19-1218
- DOI:
- 10.18653/v1/N19-1218
- Cite (ACL):
- 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.
- Cite (Informal):
- Harry Potter and the Action Prediction Challenge from Natural Language (Vilares & Gómez-Rodríguez, NAACL 2019)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/N19-1218.pdf
- Code
- aghie/hpac + additional community code