Home > Taxonomy > Event Category > Talk



Machine Reading for Everyone

Abstract: Machine reading tools such as question answering systems have the potential to accelerate tasks that involve synthesizing information buried in vast text collections.

Recent advances in training deep neural networks have produced  high performing machine reading models.  However, the current success of deep learning hinges upon having large quantities of labeled data to robustly estimate model parameters. For many languages,  little to no labeled data is available for this.


Luis Alonso-Ovalle (Department of Linguistics, McGill University)

Keep "only" strong

This event has been canceled. 



Lisa Pearl (Department of Language Science & Cognitive Sciences; University of California, Irvine)

Arguments from acquisition for how to solve the linking problem


Amy Rose Deal (Department of Linguistics, UC Berkeley)

Relative embeddings, factivity, and propositional complementation


Daniel Harbour (Department of Linguistics; Queen Mary University of London)

Frankenduals and Features Theory


Dr. Margaret Livingstone (Department of Neurobiology, Harvard Medical School)

The development of specialized modules for recognizing faces, scenes, text, and bodies: what you see is what you get.


Dr. Andrea Halpern (Department of Psychology, Bucknell University)

Imagine That! Individual Differences in Auditory Imagery for Music


Dr. Judy Kroll (Department of Psychology, Linguistics, and Women's Studies; University of California, Riverside)

The fate of the native language in second language learning: A new hypothesis about bilingualism, mind, and brain


Dr. Janet Werker (Department of Psychology, University of British Columbia)

Multisensory Foundations of Infant Speech Perception and Early Word Learning


A mechanism for syntactic category constraints in auditory word recognition

Abstract: In this talk I will describe an experiment in the visual world paradigm that aims to distinguish whether syntactic category information prevents activation of lexical candidates that don’t fit the context, or facilitates those that do.

Lunch served at 12:15.


Subscribe to Talk