Text understanding with artificial neural networks – Ondřej Bajgar
Details
Text understanding with artificial neural networks – Ondřej Bajgar
Text understanding recently became one of popular benchmarks for artificial intelligence, since answering a question using a paragraph of text often requires non-trivial reasoning.
In this talk, we will show our text understanding model based on neural networks, the Attention-Sum Reader, that performs well on several text understanding datasets. We will also present the BookTest dataset that is orders of magnitude larger than previous cloze-style text understanding datasets. The BookTest allows us to explore how far we can push the performance of a model by simply adding more data. In the last part of our talk, we explore whether the model learns any generalizable high-level reasoning skills (spoiler: the results were rather grim).
Speakers: Ondřej Bajgar - https://www.linkedin.com/in/obajgar/
Program:
- 18:00 The talk
- 20:00 Networking
Language: English
Machine Learning Meetups (MLMU) is an independent platform for people interested in Machine Learning, Information Retrieval, Natural Language Processing, Computer Vision, Pattern Recognition, Data Journalism, Artificial Intelligence, Agent Systems and all the related topics. MLMU is a regular community meeting usually consisting of a talk, a discussion and a subsequent networking allowing people to network, inspire each other and learn about exciting stuff. At the end of the year 2016, MLMU spread also to Brno and Bratislava. The beginning of 4th season brought MLMU Košice!