Grounded language learning in simulated worlds

Add to your list(s) Download to your calendar using vCal

• Felix Hill, DeepMind
• Friday 27 October 2017, 12:00-13:00
• FW26, Computer Laboratory.

If you have a question about this talk, please contact Anita Verő.

Developing systems that can execute symbolic, language-like instructions in the physical world is a long-standing challenge for Artificial Intelligence. Previous attempts to replicate human-like grounded language understanding involved hard-coding linguistic and physical principles, which is notoriously laborious and difficult to scale. Here we show that a simple neural-network based agent without any hard-coded knowledge can exploit general-purpose learning algorithms to infer the meaning of sequential symbolic instructions as they pertain to a simulated 3D world.

Beginning with no prior knowledge, the agents learn the meaning of concrete nouns, adjectives, more abstract relational predicates and longer, order-dependent, sequences of symbols. The agent naturally generalises predicates to unfamiliar objects, and can interpret word combinations (phrases) that it has never seen before. Moreover, while its initial learning is slow, the speed at which it acquires new words accelerates as a function of how much it already knows. These observations suggest that the approach may ultimately scale to a wider range of natural language, which may bring us towards machines capable of learning language via interaction with human users in the real world.

The techniques applied in this work will be covered in the course Deep Learning for NLP taught next term in the CL. https://www.cl.cam.ac.uk/teaching/1718/R228/.

Bio: Felix is a Research Scientist at Deepmind. He did his PhD at the University of Cambridge with Anna Korhonen, working on unsupervised language and representation learning with neural nets. As well as Anna, he collaborated with (and learned a lot from) Yoshua Bengio, Kyunghyun Cho and Jason Weston. As well as developing computational models that can understand language, he is interested in using models to better understand how people understand language, and is currently doing both at Deepmind.

This talk is part of the NLIP Seminar Series series.

This talk is included in these lists:

• All Talks (aka the CURE list)
• Cambridge Centre for Data-Driven Discovery (C2D3)
• Cambridge Forum of Science and Humanities
• Cambridge Language Sciences
• Cambridge talks
• Chris Davis' list
• Computer Education Research
• Computing Education Research
• Department of Computer Science and Technology talks and seminars
• FW26, Computer Laboratory
• Graduate-Seminars
• Guy Emerson's list
• Interested Talks
• Language Sciences for Graduate Students
• NLIP Seminar Series
• PMRFPS's
• Simon Baker's List
• Trust & Technology Initiative - interesting events
• bld31
• ndk22's list
• ob366-ai4er
• rp587

Note that ex-directory lists are not shown.