Keenon Werling

Learn More
The Abstract Meaning Representation (AMR) is a representation for opendomain rich semantics, with potential use in fields like event extraction and machine translation. Node generation, typically done using a simple dictionary lookup, is currently an important limiting factor in AMR parsing. We propose a small set of actions that derive AMR subgraphs by(More)
Our goal is to deploy a high-accuracy system starting with zero training examples. We consider an on-the-job setting, where as inputs arrive, we use real-time crowdsourcing to resolve uncertainty where needed and output our prediction when confident. As the model improves over time, the reliance on crowdsourcing queries decreases. We cast our setting as a(More)
This paper proposes an extension to the OpenIE paradigm, to allow the expression of recursive relations, and presents a fully implemented extension to the EXEMPLAR system, uncreatively referred to as Recursive-EXEMPLAR, to extract recursive n-ary relations automatically. A rule-based approach is shown to achieve very high accuracy. Attempts at the automatic(More)
This paper first proposes a (to the author’s limited knowledge) novel extension to the OpenIE paradigm, to allow the expression of recursive relations, and presents a fully implemented extension to the EXEMPLAR system, uncreatively referred to as Recursive-EXEMPLAR, to extract recursive n-ary relations automatically and with very high precision. It then(More)
  • 1