The need for deeper semantic processing of human language by our natural language
processing systems is evidenced by their still-unreliable performance on inferencing tasks …

We demonstrate that coreference resolution in procedural texts is significantly improved
when performing transformation-based entity linking prior to coreference relation …

Computational lexical resources such as WordNet, PropBank, VerbNet, and FrameNet are in
regular use in various NLP applications, assisting in the never-ending quest for richer, more …

Procedural texts describe dynamic state changes that occur during a step-by-step process
(eg an instruction manual, photosynthesis, or a baking recipe). As a subtask of procedural …

Understanding inferences and answering questions from text requires more than merely
recovering surface arguments, adjuncts, or strings associated with the query terms. As …

The task of entity state tracking aims to automatically analyze procedural texts–texts that
describe a step-by-step process (eg a baking recipe). Specifically, the goal is to track various …

Semantic role labeling (SRL) has multiple disjoint label sets, eg, VerbNet and PropBank.
Creating these datasets is challenging, therefore a natural question is how to use each one …

Data-driven techniques have significantly advanced the state-of-the-art in a wide range of
natural language processing (NLP) tasks. However, their primary strength lies in pattern …