James Ferguson

In this work, we present a discriminative model for detecting disfluencies in spoken language transcripts that improves upon model structures used in past work and leverages additional prosodic information. Expand

We present a method for self-training event extraction systems by bootstrapping additional training data by taking advantage of parallel mentions of the same event instance in newswire text. Expand

This document describes the University of Washington’s event extraction system used in the Event Argument Extraction and Linking and Event Nugget Detection tasks of the 2016 TAC KBP competition. Expand

We present a dataset, IIRC, with more than 13K questions over paragraphs from English Wikipedia that provide only partial information to answer them, with the missing information occurring in one or more linked documents. Expand

We formalize this problem of domain-adjacent instance identification, and introduce a novel sentence embedding approach which outperforms baselines. Expand