Predicting Linguistic Structure with Incomplete
& Cross-Lingual Supervision
Studia Linguistica Upsaliensia No. 14
By Oscar Tackstrom
Distributed By Coronet Books Inc.
$69.50 Paper original
Contemporary approaches to natural language processing are predominantly based on statistical machine learning from large amounts of text, which has been manually annotated with the linguistic structure of interest. However, such complete supervision is currently only available for the world's major languages, in a limited number of domains and for a limited range of tasks. As an alternative, this dissertation considers methods for linguistic structure prediction that can make use of incomplete and cross-lingual supervision, with the prospect of making linguistic processing tools more widely available at a lower cost. An overarching theme of this work is the use of structured discriminative latent variable models for learning with indirect and ambiguous supervision; as instantiated, these models admit rich model features while retaining efficient learning and inference properties.
Return to Coronet Books main page