In this paper, we present a unified knowledge based approach for sense disambiguation and semantic role labeling. Our approach performs both tasks through a single algorithm that ...
Extending a machine learning based coreference resolution system with a feature capturing automatically generated information about semantic roles improves its performance.
e, the system labels constituents with either abstract semantic roles such as AGENT or PATIENT, or more domain-specific semantic roles such as SPEAKER, MESSAGE, and TOPIC. The syst...
We present the methodology that underlies new metrics for semantic machine translation evaluation that we are developing. Unlike widely-used lexical and n-gram based MT evaluation...
In Semantic Role Labeling (SRL), arguments are usually limited in a syntax subtree. It is reasonable to label arguments locally in such a sub-tree rather than a whole tree. To ide...