Percy Liang, Michael Jordan, and Dan Klein. Learning
correspondences with less supervision. ACL-IJCNLP 2009.
Considers how we might learn the
correspondence between a textual description of an event and a
structured (data base) with information (data base records) on the same
event. Allows for the possibility that some information may
appear only in the text, some only in the data base. Builds a
3-level generative model (select records to report; select fields
in records to report; generates words for field), then uses EM to
align the model with the text, setting parameters for each level.
Evaluated in terms of quality of alignment.
Hoifung Poon and Pedro Domingos. Unsupervised
parsing. EMNLP 2009.
Seeks to do unsupervised semantic
analysis starting from dependency trees. Builds clusters of synonymous
syntactic and semantic relations in order to account for paraphrases
both at the syntactic level and the semantic level. Evaluates success
by generating logical forms for a collection of GENIA abstracts and
then answering questions about these texts by matching logical forms.
Coming next: anaphora resolution.