::Stanford University::United States::United Nations
Processing Parasitic Gaps
Time to get some actual data.
Evidential Marking and Hedging
Using betting market data to explore how people express sources of evidence, confidence, and tolerance for imprecision linguistically.
Asymmetric Association Measures
Most computational measures of word association are symmetric while most humage judgements of word association are not. Exploring the use of psycholinguistic data for building better association metrics.
Countability and the Mass Count Distinction
A theoretical overiew of the relationship between Extension, Ontological Type and Morphosyntactic Class with experimental evidence. See the presentation.
How universal is the universal grinder? Evidence from Mechanical Turk acceptability judgements. See the presentation.
Processing Factors Influencing Acceptability in Extractions from Complex Subjects
Unpublish manuscript that explores the processing factors influencing the accptability of filler-gap dependencies where the gap is located within a Complex Subject NP. See the pdf, the CUNY 2011 poster and the abstract.
HedgeHunter: A System for Hedge Detection and Uncertainty Classification
Hedge detection and uncertainty classification are important components of a high precision IE system. This paper describes a two part supervised system which classifies words as hedge or non-hedged and sentences as certain or uncertain in biomedical and Wikipedia data. See the pdf.
Pressupostions in Natural Language Inference
Using factive presuppositions to improve the performance Bill MacCartney's NatLog textual entailment system. See the pdf.
Rebuilding the Tower