Noah Smith designs algorithms for automated analysis of human language. He often exploits the web to this end, including mining the web for translations (Resnik and Smith, 2003), measuring public opinion from social messages (O'Connor et al., 2010), and inferring geographic linguistic variation (Eisenstein et al., 2010).
|| نوح سميث
|Photo by Karen Meyers.|
Smith has also contributed algorithms tackling the core problems of natural language processing: parsing sentences into syntactic representations (Eisner et al., 2005; Martins et al., 2009) and semantic representations (Das et al., 2010), as well as cross-cutting techniques for unsupervised language learning (Smith and Eisner, 2005; Cohen and Smith, 2009). His 2011 book, Linguistic Structure Prediction, synthesizes many statistical modeling techniques for language.
Such methods advance applications for automatic translation (Al-Onaizan et al., 1999; Gimpel and Smith, 2011), text-driven forecasting (Kogan et al., 2009; Yano et al., 2009), education (Heilman and Smith, 2010), and other next-generation language technologies.
Smith is the Finmeccanica Associate Professor of Language Technologies and Machine Learning in the School of Computer Science at Carnegie Mellon University. Prior to
coming to CMU, he was a Hertz
Foundation Fellow at Johns Hopkins
University, where he completed his Ph.D. in 2006. He is a clarinetist, tanguero, and swimmer.
Active courses at CMU:
- Probabilistic Graphical Models: advanced graduate course in machine learning, taught Fall 2010
- Text-Driven Forecasting: seminar-project hybrid course for graduate students, taught Fall 2009
- Language and Statistics II: advanced statistical NLP for graduate students, taught Fall 2006, Fall 2007, Fall 2008, and Fall 2009
- Empirical Research Methods in Computer Science (JHU, Fall 2005)
- Computational Genomics: Sequence Modeling (JHU, Fall 2004)
- Hidden Markov Models: All the Glorious Gory Details (October, 2004)
- Log-Linear Models (December, 2004)
- Predicting English (JHU CLSP summer workshop lab with Jason Eisner, Summers 2002 and 2003, taught by others since); read the paper
Research in NLP (Natural Language Processing)
How can computer programs intelligently process text
data? My research brings together linguistic abstractions,
statistical reasoning, and computational formalisms
to develop general
NLP methods and models. The results
are used in software applications (e.g., machine translation,
information extraction, text mining, question answering, and
text-driven forecasting) and also serve scientific discovery wherever text
serves as data (e.g., sociolinguistics, political science, and