Author: Dayne Freitag

We simulate the process of corpus review and word list creation, showing that several simple interventions greatly improve recall as a function of simulated labor.

We present VALET, a framework for rule-based information extraction written in Python. We show how a handful of rules suffices to implement sophisticated matching, and describe a user interface that facilitates exploration for development and maintenance of rule sets.

We consider the use of distant supervision for biological information extraction, and introduce two understudied corpora of this form, the Biological Expression Language (BEL) Large Corpus and the Pathway Logic (PL) Datum Corpus.

We describe a method for identifying and performing functional analysis of structured regions that are embedded in natural language documents, such as tables or key-value lists.

We present initial work that uses significant patterns to generate extraction rules, and conclude with a discussion of future directions of our work.

We describe a 460-million word corpus of online discussions.

We describe a discriminatively trained sequence alignment model based on the averaged perceptron. In common with other approaches to sequence modeling using perceptrons, and in contrast with comparable generative models, this model permits and transparently exploits arbitrary features of input strings.

We generated a TOEFL-like test using WordNet, containing thousands of questions and composed only of words occurring with sufficient corpus frequency to support sound distributional comparisons.

We address the problem of learning a morphological automaton directly from a monolingual text corpus without recourse to additional resources.