Climbing the Tower of Babel: Unsupervised Multilingual Learning

For centuries, scholars have explored the deep links among human languages. In this paper, we present a class of probabilistic models that use these links as a form of naturally occurring supervision. These models allow us to substantially improve performance for core text processing tasks, such as morphological segmentation, part-of-speech tagging, and syntactic parsing. Besides these traditional NLP tasks, we also present a multilingual model for the computational decipherment of lost languages.

• Type: Conference
• Year: 2010
• Where: ICML
• Authors: Benjamin Snyder, Regina Barzilay
• Keywords: ICML 2010, Machine Learning, Probabilistic Models, Text Processing Tasks, Traditional Nlp Tasks