Language-Independent Discriminative Parsing of Temporal Expressions
Venue
The 51st Annual Meeting of the Association for Computational Linguistics (ACL 2013) (to appear)
Publication Year
2013
Authors
Gabor Angeli, Jakob Uszkoreit
BibTeX
Abstract
Temporal resolution systems are traditionally tuned to a particular language,
requiring significant human effort to translate them to new languages. We present a
language independent semantic parser for learning the interpretation of temporal
phrases given only a corpus of utterances and the times they reference. We make use
of a latent parse that encodes a language-flexible representation of time, and
extract rich features over both the parse and associated temporal semantics. The
parameters of the model are learned using a weakly supervised bootstrapping
approach, without lexical cues or language-specific tuning. We achieve
state-of-the-art accuracy on all languages in the TempEval-2 temporal normalization
task, reporting a 4% improvement in both English and Spanish accuracy, and to our
knowledge the first results for four other languages.
