Paul Smolensky

Predicting the Argumenthood of English Prepositional Phrases

2018 · arXiv (Cornell University)

Distinguishing between arguments and adjuncts of a verb is a longstanding, nontrivial problem. In natural language processing, argumenthood information is important in tasks such as semantic role labeling (SRL) and prepositional phrase (PP) attachment disambiguation. …

Enhancing the Transformer with Explicit Relational Encoding for Math Problem Solving

2019 · arXiv (Cornell University)

We incorporate Tensor-Product Representations within the Transformer in order to better support the explicit representation of relation structure. Our Tensor-Product Transformer (TP-Transformer) sets a new state of the art on the recently-introduced Mathematics Dataset containing …