Paper: Joint Inference for Natural Language Processing

ACL ID W09-1101
Title Joint Inference for Natural Language Processing
Venue International Conference on Computational Natural Language Learning
Session Main Conference
Year 2009

of the Invited Talk In recent decades, researchers in natural language processing have made great progress on well- defined subproblems such as part-of-speech tagging, phrase chunking, syntactic parsing, named-entity recognition, coreference and semantic-role label- ing. Better models, features, and learning algorithms have allowed systems to perform many of these tasks with 90% accuracy or better. However, success in in- tegrated, end-to-end natural language understanding remains elusive. I contend that the chief reason for this failure is that errors cascade and accumulate through a pipeline of naively chained components. For exam- ple, if we naively use the single most likely output of a part-of-speech tagger as the input to a syntactic parser, and those parse trees as the input to a co...