As part of the 3rd edition of the Lecture series by Young Doctors (DEEC-JD3), the 4th lecture of the cycle will take place on March 11th, 2020, at 12:00, in the EA2 amphitheater.

(POSTPONED TO DATE TO BE ANNOUNCED)

Title: Learning to Represent Variation in Linguistic Data.

Speaker: Wilker Aziz, Assistant Professor in computational linguistics at the University of Amsterdam

Abstract: A defining feature of natural languages is variation: ideas can be expressed in different ways; different words mean the same; the same words mean differently. There's variation that's inherent to linguistic devices (morphology, syntax, discourse), there's variation due to background of the speaker, there's variation that's used to convey opinions and/or imbue one with emotions, there's variation due to seemly arbitrary confounders such as fatigue, concentration level, and boredom. Despite this unavoidable truth, many of the state-of-the-art models for natural language processing cannot account for unobserved factors of variation, instead conflating such factors under a single hypothesis. In this talk he will discuss how to equip these models with statistical tools that promote an explicit account of variation and demonstrate a few applications aimed at different levels of linguistic variability (e.g. sentence-level, word-level, and subword-level). He will close the talk with thoughts on the role of inductive biases such as multimodality and sparsity in the learning of disentangled factors of variation.