Elamur Research⌕
☰
home / papers / 2019 / Learning to Speak and Act in a Fantasy Text Adventure Game

Learning to Speak and Act in a Fantasy Text Adventure Game

Paper · 2019 · Jack Urbanek, Angela Fan, Siddharth Karamcheti et al.

Summary

Most dialogue systems learn only from text and never connect words to a world they can perceive or change. The authors address this with LIGHT, a multi-player fantasy text adventure in the style of a MUD. Humans and models both play characters who can talk, perform physical actions and express emotes. Nearly everything was written by crowdworkers: places, items with their affordances, characters with personas, and about 11k recorded human-human role-play episodes.

On this data the authors train generative and retrieval models, including two BERT adaptations. One is a fast bi-ranker; the other is a slower cross-ranker that models richer context-response interactions. Both beat earlier baselines. Ablation studies show that information about the local scene, the characters present and earlier actions improves the prediction of utterances, actions and emotes. Past dialogue turns out to be the single most essential input.

Even the best models remain below human performance. This makes LIGHT an open benchmark for grounded, embodied language learning. It is released through ParlAI.

Key points

  • The crowdsourced world contains 663 locations drawn from 37 categories, 3462 objects and 1755 characters, all described in natural language.
  • The training split holds 8538 dialogues with 110,877 utterances. A "Test Unseen" split uses 6 held-out location categories, such as underwater aquapolis and netherworld, to measure generalization.
  • Agents can use physical actions (get, drop, put, give, steal, wear, eat, hit and others), which change the game state, and 22 emotes, which do not.
  • Models compared include generative Transformers and the BERT-based Bi-Ranker and Cross-Ranker. Persona features help noticeably, while object descriptions add the least.
  • Qualitative tests show that changing the setting or the partner changes the predictions. For example, a request for an item leads the model to fetch it, with the response depending on who asked.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Stanford UniversityStanford · United States506 works · 330,052 citations🏢MetaMenlo Park · United States214 works · 241,492 citations🎓University College LondonLondon · United Kingdom107 works · 22,923 citations🏢Meta (Israel)Tel Aviv · Israel46 works · 42,810 citations🏢Meta (United Kingdom)London · United Kingdom54 works · 19,348 citations🔬Laboratoire Lorrain de Recherche en Informatique et ses ApplicationsNancy · France32 works · 4,142 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 18,614 worksArtificial Intelligence · 17,965 worksArts and Humanities · 17,450 worksLanguage and Linguistics · 17,296 works

Cite

Cite as Jack Urbanek, Angela Fan, Siddharth Karamcheti, Saachi Jain, Samuel Humeau, Emily Dinan, Tim Rocktaschel, Douwe Kiela, Arthur Szlam and Jason Weston. 2019. Learning to Speak and Act in a Fantasy Text Adventure Game. arXiv:1903.03094.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.1903.03094 · arXiv 1903.03094

@misc{urbanek2019learning,
  title = {{Learning to Speak and Act in a Fantasy Text Adventure Game}},
  author = {Jack Urbanek, Angela Fan, Siddharth Karamcheti, Saachi Jain, Samuel Humeau, Emily Dinan, Tim Rocktaschel, Douwe Kiela, Arthur Szlam and Jason Weston},
  year = {2019},
  doi = {10.48550/arxiv.1903.03094},
  eprint = {1903.03094},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.1903.03094}
}

References

48 references, 17 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Stanislaw Antol, Aishwarya Agrawal, Jiasen Lu, Margaret Mitchell, Dhruv Batra, C Lawrence Zitnick, and Devi Parikh. 2015. Vqa: Visual question answering. In Proceedings of the IEEE international conference on computer vision, pages 2425–2433. find
  2. Antoine Bordes, Y-Lan Boureau, and Jason Weston. 2017. Learning end-to-end goal-oriented dialog. In Proceedings of the International Conference on Learning Representations (ICLR). find
  3. Antoine Bordes, Nicolas Usunier, Ronan Collobert, and Jason Weston. 2010. Towards understanding situated natural language. In Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, pages 65–72. find
  4. Simon Brodeur, Ethan Perez, Ankesh Anand, Florian Golemo, Luca Celotti, Florian Strub, Jean Rouat, Hugo Larochelle, and Aaron Courville. 2017. Home: A household multimodal environment. arXiv preprint arXiv:1711.11017. — [arXiv:1711.11017](https://arxiv.org/abs/1711.11017) find
  5. Rodney A Brooks. 1991. Intelligence without representation. Artificial intelligence, 47(1-3):139–159. find
  6. Angel Chang, Angela Dai, Thomas Funkhouser, Maciej Halber, Matthias Nießner, Manolis Savva, Shuran Song, Andy Zeng, and Yinda Zhang. 2017. Matterport3d: Learning from rgb-d data in indoor environments. arXiv preprint arXiv:1709.06158. — [arXiv:1709.06158](https://arxiv.org/abs/1709.06158) find
  7. Marc-Alexandre Côté, Ákos Kádár, Xingdi Yuan, Ben Kybartas, Tavian Barnes, Emery Fine, James Moore, Matthew Hausknecht, Layla El Asri, Mahmoud Adada, et al. 2018. Textworld: A learning environment for text-based games. arXiv preprint arXiv:1806.11532.
  8. Abhishek Das, Satwik Kottur, Khushi Gupta, Avi Singh, Deshraj Yadav, José MF Moura, Devi Parikh, and Dhruv Batra. 2017. Visual dialog. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, volume 2. find
  9. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. CoRR, abs/1810.04805.
  10. Edward Dieterle. 2009. Multi-user virtual environments for teaching and learning. In Encyclopedia of Multimedia Technology and Networking, Second Edition, pages 1033–1041. IGI Global. find
  11. Emily Dinan, Varvara Logacheva, Valentin Malykh, Alexander Miller, Kurt Shuster, Jack Urbanek, Douwe Kiela, Arthur Szlam, Iulian Serban, Ryan Lowe, et al. 2019a. The second conversational intelligence challenge (convai2). arXiv preprint arXiv:1902.00098.
  12. Emily Dinan, Stephen Roller, Kurt Shuster, Angela Fan, Michael Auli, and Jason Weston. 2019b. Wizard of Wikipedia: Knowledge-powered conversational agents. In Proceedings of the International Conference on Learning Representations (ICLR).
  13. Michael Fleischman and Deb Roy. 2005. Intentional context in situated natural language learning. In Proceedings of the Ninth Conference on Computational Natural Language Learning, pages 104–111. Association for Computational Linguistics. find
  14. Jon Gauthier and Igor Mordatch. 2016. A paradigm for situated and goal-driven language learning. arXiv preprint arXiv:1610.03585. — [arXiv:1610.03585](https://arxiv.org/abs/1610.03585) find
  15. Matthew Henderson, Blaise Thomson, and Jason D Williams. 2014. The second dialog state tracking challenge. In Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL), pages 263–272. find
  16. Matthew Johnson, Katja Hofmann, Tim Hutton, and David Bignell. 2016. The malmo platform for artificial intelligence experimentation. In IJCAI, pages 4246–4247. find
  17. Armand Joulin, Edouard Grave, Piotr Bojanowski, and Tomas Mikolov. 2016. Bag of tricks for efficient text classification. arXiv preprint arXiv:1607.01759. find
  18. Rafal Jozefowicz, Oriol Vinyals, Mike Schuster, Noam Shazeer, and Yonghui Wu. 2016. Exploring the limits of language modeling. arXiv preprint arXiv:1602.02410. find
  19. Douwe Kiela, Luana Bulat, Anita L Vero, and Stephen Clark. 2016. Virtual embodiment: A scalable long-term strategy for artificial intelligence research. arXiv preprint arXiv:1610.07432. — [arXiv:1610.07432](https://arxiv.org/abs/1610.07432) find
  20. Eric Kolve, Roozbeh Mottaghi, Daniel Gordon, Yuke Zhu, Abhinav Gupta, and Ali Farhadi. 2017. Ai2-thor: An interactive 3d environment for visual ai. arXiv preprint arXiv:1712.05474.
  21. Brenden M Lake, Tomer D Ullman, Joshua B Tenenbaum, and Samuel J Gershman. 2017. Building machines that learn and think like people. Behavioral and Brain Sciences, 40. find
  22. Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. In European conference on computer vision, pages 740–755. Springer.
  23. Laurens van der Maaten and Geoffrey E. Hinton. 2008. Visualizing data using t-sne. find
  24. P.-E. Mazaré, S. Humeau, M. Raison, and A. Bordes. 2018. Training Millions of Personalized Dialogue Agents. ArXiv e-prints.
  25. Tomas Mikolov, Armand Joulin, and Marco Baroni. 2016. A roadmap towards machine intelligence. In International Conference on Intelligent Text Processing and Computational Linguistics, pages 29– 61. Springer. find
  26. A. H. Miller, W. Feng, A. Fisch, J. Lu, D. Batra, A. Bordes, D. Parikh, and J. Weston. 2017. Parlai: A dialog research software platform. arXiv preprint arXiv:1705.06476.
  27. Nasrin Mostafazadeh, Chris Brockett, Bill Dolan, Michel Galley, Jianfeng Gao, Georgios P Spithourakis, and Lucy Vanderwende. 2017. Image-grounded conversations: Multimodal context for natural question and response generation. arXiv preprint arXiv:1701.08251.
  28. Karthik Narasimhan, Tejas Kulkarni, and Regina Barzilay. 2015. Language understanding for text-based games using deep reinforcement learning. arXiv preprint arXiv:1506.08941.
  29. Junhyuk Oh, Satinder Singh, Honglak Lee, and Pushmeet Kohli. 2017. Zero-shot task generalization with multi-task deep reinforcement learning. arXiv preprint arXiv:1706.05064. — [arXiv:1706.05064](https://arxiv.org/abs/1706.05064) find
  30. Ramakanth Pasunuru and Mohit Bansal. 2018. Game-based video-context dialogue. arXiv preprint arXiv:1809.04560. find
  31. Jeffrey Pennington, Richard Socher, and Christopher D. Manning. 2014. Glove: Global vectors for word representation. In EMNLP.
  32. Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019. Language models are unsupervised multitask learners. find
  33. Manolis Savva, Angel X Chang, Alexey Dosovitskiy, Thomas Funkhouser, and Vladlen Koltun. 2017. Minos: Multimodal indoor simulator for navigation in complex environments. arXiv preprint arXiv:1712.03931. — [arXiv:1712.03931](https://arxiv.org/abs/1712.03931) find
  34. Rico Sennrich, Barry Haddow, and Alexandra Birch. 2016. Neural machine translation of rare words with subword units. In ACL.
  35. Kurt Shuster, Samuel Humeau, Antoine Bordes, and Jason Weston. 2018. Engaging image chat: Modeling personality in grounded dialogue. arXiv preprint arXiv:1811.00945. — [arXiv:1811.00945](https://arxiv.org/abs/1811.00945) find
  36. Alessandro Sordoni, Michel Galley, Michael Auli, Chris Brockett, Yangfeng Ji, Margaret Mitchell, Jian-Yun Nie, Jianfeng Gao, and Bill Dolan. 2015. A neural network approach to context-sensitive generation of conversational responses. arXiv preprint arXiv:1506.06714.
  37. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems, pages 5998–6008.
  38. Oriol Vinyals and Quoc Le. 2015. A neural conversational model. In Proceedings of the 31st International Conference on Machine Learning, Deep Learning Workshop, Lille, France.
  39. Harm de Vries, Kurt Shuster, Dhruv Batra, Devi Parikh, Jason Weston, and Douwe Kiela. 2018. Talk the walk: Navigating new york city through grounded dialogue. arXiv preprint arXiv:1807.03367. find
  40. Sida I Wang, Samuel Ginn, Percy Liang, and Christoper D Manning. 2017. Naturalizing a programming language via interactive learning. arXiv preprint arXiv:1704.06956. find
  41. Sida I Wang, Percy Liang, and Christopher D Manning. 2016. Learning language games through interaction. arXiv preprint arXiv:1606.02447. find
  42. Thomas Wolf, Victor Sanh, Julien Chaumond, and Clement Delangue. 2019. Transfertransfo: A transfer learning approach for neural network based conversational agents. arXiv preprint arXiv:1901.08149. find
  43. Ledell Yu Wu, Adam Fisch, Sumit Chopra, Keith Adams, Antoine Bordes, and Jason Weston. 2018a. Starspace: Embed all the things! In Thirty-Second AAAI Conference on Artificial Intelligence. find
  44. Yi Wu, Yuxin Wu, Georgia Gkioxari, and Yuandong Tian. 2018b. Building generalizable agents with a realistic and rich 3d environment. arXiv preprint arXiv:1801.02209. — [arXiv:1801.02209](https://arxiv.org/abs/1801.02209) find
  45. Zhilin Yang, Saizheng Zhang, Jack Urbanek, Will Feng, Alexander H Miller, Arthur Szlam, Douwe Kiela, and Jason Weston. 2017. Mastering the dungeon: Grounded language learning by mechanical turker descent. arXiv preprint arXiv:1711.07950. find
  46. Kexin Yi, Jiajun Wu, Chuang Gan, Antonio Torralba, Pushmeet Kohli, and Josh Tenenbaum. 2018. Neural-symbolic vqa: Disentangling reasoning from vision and language understanding. In Advances in Neural Information Processing Systems, pages 1039–1050.
  47. Haonan Yu, Jiang Wang, Zhiheng Huang, Yi Yang, and Wei Xu. 2016. Video paragraph captioning using hierarchical recurrent neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4584–4593. find
  48. Saizheng Zhang, Emily Dinan, Jack Urbanek, Arthur Szlam, Douwe Kiela, and Jason Weston. 2018. Personalizing dialogue agents: I have a dog, do you have pets too? In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, pages 2204–2213, Melbourne, Australia. Associat…

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/urbanek-2019-learning-speak-act-fantasy-text/