Noah's

ARK researchers in May 2011. Picture by Greg Hanneman.

Noah's ARK^[1] is Noah Smith's informal research group at the Language Technologies Institute, School of Computer Science, Carnegie Mellon University. (The research is formal; the group is informal.) As you may have guessed, our research focuses on problems of ambiguity and uncertainty in natural language processing, including morphology, syntax, semantics, translation, and behavioral/social phenomena observed through language—all viewed through a computational lens.

^[1]The acronym is ambiguous; possible interpretations might include Ambiguity Research Kith or Ambiguity Resolution K. or A. R. Kibbutz. With apologies to the Bible and DAGS.

ARK Research: Awards, News Coverage

ARK researchers in April 2009. Picture by Mattt Thompson.

Demos

A coreference system by Brendan O'Connor and Michael Heilman.
A parse tree visualizer by Brendan O'Connor.

Resources and Tools

The following were developed by ARK researchers (*developed in whole or in part before joining ARK):

NLP tools: universal part-of-speech tagset, set of twelve coarse POS tags that generalizes across several languages; SEMAFOR, an open-source statistical frame-semantic parser; TurboParser, an open-source, trainable statistical dependency parser based on integer linear programming; MSTParserStacked, an open-source, trainable statistical dependency parser based on stacking; DAGEEM code for unsupervised dependency grammar induction; *Dyna, a declarative programming language for dynamic programming algorithms
Machine translation tools, including: *cdec, a framework for statistical translation and other structure prediction problems; *Egypt, a statistical machine translation toolkit that includes Giza; gappy pattern models, code for modeling monolingual and bilingual textual patterns with gaps; Rampion, a training algorithm for statistical machine translation models
Social media tools, including: Twitter NLP resources
Datasets: *STRAND (parallel text collections from the web); CURD (the Carnegie Mellon University Recipe Database); 10-K Corpus (companies' annual reports and stock return volatility data); political blog corpus; movie$ corpus; question-answer data; Congressional bills corpus

Projects

This is a list of multi-PI sponsored projects; it is not an exhaustive list of ARK research activities!

AQMAR project on Arabic NLP
INCA project for multiprocessor machine translation

Past projects:

RAVINE project to explore news through quotes

Researchers

Name	Position	Topics	Languages (Spoken and/or Written)	Languages (Researched)	Languages (Hacked In)	Favorite Term of Venery
Waleed Ammar	Ph.D. student, LTI	statistical machine translation, text analytics	Arabic, English	English, Arabic, Hebrew	C#, C/C++, Javascript, ruby, Java, PHP, ASP.net	charm
David Bamman	Ph.D. student, LTI	sociolinguistic variation; statistical NLP for computational social science and the humanities	English, Latin, Ancient Greek, Italian (un po), French (un peu), German (ein bisschen), Mandarin Chinese (一点儿)	English, Latin, Ancient Greek, Chinese	Java, Python, Perl	coalition
Victor Chahuneau	M.S. student, LTI
Dipanjan Das	Ph.D. student, LTI	semantic and syntactic parsing, sentence-sentence semantic relationships, semi-supervised learning	English, Bengali, Hindi, Sanskrit (swalpam)	English, Bengali	Java, C, C++, Perl	bloat
Chris Dyer	Post-doc, LTI	machine translation, unsupervised learning, text-based forecasting, big data	English, German	Arabic, Chinese, Czech, Dutch, English, French, German, Hungarian, Telugu, Turkish, Urdu, Welsh	C++, Perl, Java	conspiracy
Kevin Gimpel	Ph.D. student, LTI	statistical NLP and translation	English, German, Italian	English, Portuguese, German, Chinese, Arabic, Spanish, French, Urdu	C/C++, Perl, Java, Matlab	crash
André Martins	Ph.D. student, LTI and Universidade Técnica de Lisboa	structured and kernel machine learning, parsing	Portuguese, English, Spanish, German (ein bisschen), French (un petit peu)	Portuguese, English, Spanish	C, C++, Matlab	scurry
Behrang Mohit	Post-doc, CMU-Q	Arabic NLP, machine translation, semantics	English, Persian (Farsi), Arabic	English, Arabic	Java, Python
Brendan O'Connor	Ph.D. student, MLD	text analysis and social science	English, German	English, Chinese	R, Awk, etc.	prickle
Nathan Schneider	Ph.D. student, LTI	linguistic structure discovery; semantics; cognitive linguistics	English, Hebrew (קצת), Arabic (قليل), French (un peu), German (ein bisschen)	English, Hebrew	Python, Java, PHP, Scheme, Javascript	smack
Yanchuan Sim	Ph.D. student, LTI	Bayesian graphical modeling, text mining	English, Chinese (Mandarin, Teochew, Cantonese, Hokkien)	English	C/C++, Java, Python	exaltation
Tae Yano	Ph.D. student, LTI	NLP in the political domain, rich models of structured NL data (e.g., blogs)	Japanese, English, Spanish, French	English	C, C++, Java, Perl, Python	husk
Dani Yogatama	M.S. student, LTI	text-driven forecasting	Indonesian, Japanese, English	English, Japanese, French, Spanish	C/C++, Java, Python, Matlab	band
Bryan Routledge	Associate Professor of Finance, Tepper	Finance, asset pricing	English, Canadian	N/A	Matlab, R, Stata, Perl, Excel, Cobol	pod
Noah Smith	Associate Professor, LTI & MLD	(all of the above)	English, French (un peu)	Arabic, Bulgarian, Czech, English, French, German, Hebrew, Korean, Mandarin, Portuguese, Turkish	LaTeX	parade

Alumni

(If you're one of these people and the information below is not current, it's time to get in touch!)

Shay Cohen, Ph.D. '11 → Postdoctoral Fellow, Columbia University
Michael Heilman, Ph.D. '11 [proof] → Associate Research Scientist, Educational Testing Service

Rishav Bhowmick, B.S. '10 (CMU-Q)
Desai Chen, B.S. '11 → MIT CSAIL Ph.D. program
Philip Gianfortoni, B.S. '09 (research programmer) → LTI M.S. program
Mohammad Haque, B.S. '10 → Endeca
Dimitry Levin, B.S. '08 → Citigroup
Zack McCord
Zach Paine, B.S. '08 (research programmer) → Google
Neel Shah, B.S. '10
Cari (Sisson) Bader, M.S. '08 [proof] → Lyrix → Nuance
Dan Tasse, B.S. '08 → Google
Mattt Thompson, B.A. '09 → Cerego
Mengqiu Wang, M.S. '07 → Stanford Ph.D. program

Acknowledgments

Our research has been/is supported in part by the DARPA Computer Science Study Panel program (grant numbers HR-00110110013, NBCH-1080004, and N10AP20042), IARPA (grant number N10PC20222), the National Science Foundation (grant numbers IIS-0713265, IIS-0836431, IIS-0844507, IIS-0915187, CAREER IIS-1054319, and a graduate fellowship to Michael Heilman), the Army Research Office (grant number W911NF-10-1-0533), the Qatar National Research Foundation (grant number NPRP 08-485-1-083), Sandia National Laboratories (a graduate fellowship to Kevin Gimpel), the Information and Communication Technologies Institute (a graduate fellowship to André Martins), the Singapore Agency for Science, Technology, and Research (a graduate fellowship to Yanchuan Sim), a gift from the Berkman Faculty Development Fund at CMU, an IBM faculty award, a Q-Group award, grants from Google, and computational resources provided by Yahoo, the Pittsburgh Supercomputing Center, and Amazon Web Services.