Events Calendar

Can machines understand and generate stories?

Speaker: Angeliki Lazaridou, USC/ISI Summer Intern

Talk Title: Can machines understand and generate stories?

Series: Natural Language Seminar

Abstract: Computational creativity is an emerging field of AI, with linguistic creativity being an interesting test-bed for developing and evaluating machines with reasoning capabilities. A concrete example is story generation and understanding, a task which unlike the vast majority of traditional NLP that treats sentences in isolation, requires deep understanding of the general context and discourse of stories.

In this talk, I will present some preliminary steps towards this goal and show how sequence-to-sequence models can be applied to this task. Overall, our results on story understanding are on par with current state-of-the-art (that nevertheless have no generative capabilities), while at the same time producing sometimes rather amusing story endings.


Biography: Angeliki is a final year PhD student at the Center for Mind/Brain Sciences of the University of Trento. She received her MSc from the Saarland University, where she worked with Ivan Titov and Caroline Sporleder on Bayesian models for sentiment and discourse. She is currently working at the intersection between language and vision under the supervision of Marco Baroni.

Host: Xing Shi and Kevin Knight

More Info: http://nlg.isi.edu/nl-seminar/

Webcast: http://webcastermshd.isi.edu/Mediasite/Play/202452984a364bc8875b71bf115149281d

Location: Information Science Institute (ISI) - 11th Flr Conf Rm # 1135, Marina Del Rey

WebCast Link: http://webcastermshd.isi.edu/Mediasite/Play/202452984a364bc8875b71bf115149281d

Audiences: Everyone Is Invited

Contact: Peter Zamar

Event Link: http://nlg.isi.edu/nl-seminar/