Nathan Schneider www.nathan.cl
nschnOBSCUREeid@cs.cmu.edu

Academic background

University of Edinburgh September 2014–Present
Institute for Language, Cognition and Computation
School of Informatics
Edinburgh, Scotland, UK

Postdoctoral researcher with Mark Steedman.

Research topic: computational modeling of grammar and meaning

Carnegie Mellon University August 2008–August 2014
Language Technologies Institute
School of Computer Science
Pittsburgh, PA

Ph.D. work in statistical natural language processing, advised by Noah Smith.

Research topics: machine learning for NLP, semantics, named entity recognition, corpus annotation, social media text, nonnative writing, Arabic NLP, text visualization

Dissertation: Lexical Semantic Analysis in Natural Language Text. (Defended June 19, 2014; submitted September 30, 2014.)

Information Sciences Institute, June 2012–August 2012
University of Southern California
Los Angeles, CA

Summer research intern with Kevin Knight.

Research topic: semantics for machine translation

University of California, Berkeley August 2004–May 2008
Berkeley, CA

B.A. with High Honors; Double Major in Computer Science (with Honors), Linguistics
Honors: Phi Beta Kappa; Computer Science Faculty Commendation

Research topics: construction grammar formalisms, Hebrew morphology, semantics, metonymy recognition, statistical news analysis
Thesis: “Hebrew Verb Morphology and Embodied Construction Grammar”

Industry experience

Microsoft May 2007–August 2007
Redmond, WA

Role: Software Development Intern
In the Office Sharepoint Search group, worked on designing and implementing a new feature for the next version of Office

Convergys June 2006–August 2006
Cincinnati, OH

Role: Software Intern
Involved in various aspects of the planning, development, and testing phases of customizations of a Java web application

CAD Centric Systems June 2003–July 2003
Cincinnati, OH

Role: Software Intern
Web design work, including use of Macromedia Flash

Teaching & mentorship

Foundations of Natural Language Processing (INFR09028) Spring 2016
University of Edinburgh

I expect to co-teach (along with Sharon Goldwater) this course for third-year undergraduates.

Edinburgh MSc thesis projects supervised in 2015

• Marco Damonte, “Machine Translation with Coarse Lexical Semantics” (co-supervised with Alexandra Birch)
• Nora Hollenstein, “Inconsistency Detection in Semantic Annotation” (co-supervised with Bonnie Webber)
• Ye Yang, “Recognizing Annotator Behavior in Crowdsourcing” (co-supervised with Bonnie Webber)
• Felisia Loukou, “Light Verb Constructions in Distributional Entailment Graphs” (co-supervised with Mark Steedman and Omri Abend)

Committee member

• Liane Guillou (Edinburgh Informatics Ph.D. student 3rd year review, 2015-01-22)
• Federico Fancellu (Edinburgh Informatics Ph.D. student 1st year review, 2015-09-30)

Natural Language Processing (11-411) Spring 2011
Carnegie Mellon University

Role: Teaching assistant
Lectures: Lexical Semantics; Semantic Role Labeling and Relational Semantics

Advanced NLP Seminar (11-713) Spring 2010
Carnegie Mellon University

Role: Teaching assistant

Neural Basis of Thought and Language (CS C182) Spring 2008
University of California, Berkeley

Role: Course reader
Lecture: A Symbolic Formalism for Embodied Grammar

Structure and Interpretation of Computer Programs (CS 61A) Spring 2006
University of California, Berkeley

Role: Lab assistant

Tutorials

The Logic of AMR: Practical, Unified, Graph-Based Sentence Semantics for NLP 2015-05-31
NAACL-HLT conference, Denver, CO

Co-presenters: Jeffrey Flanigan, Tim O’Gorman
Length: 3 hours

Getting the Roles Right: Using FrameNet in NLP 2015-05-31
NAACL-HLT conference, Denver, CO

Co-presenters: Collin Baker, Miriam R. L. Petruck, Michael Ellsworth
Length: 3 hours

Presentations

• Dealing With Off-the-Charts Polysemy in English Prepositions: Representation, Annotation, and Disambiguation. Saarland University FEAST series (2015-10-20).
• Struggling with English prepositional verbs. Talk at ICLC 2015, Newcastle, England.
• Hacking a Way Through the Twitter Language Jungle: Syntactic Annotation, Tagging, and Parsing of English Tweets. Keynote at Workshop on Natural Language Processing for Informal Text, Rotterdam (2015-06-23).
• Semantic Abstraction at Scale: Opportunities and Challenges for NLP with the FrameNet and AMR Representations.
  • Invited talk at the Swedish FrameNet++ Workshop, University of Gothenburg Språkbanken Group (2014-11-19).
  • Google Mountain View (2015-02-06).
  • Bielefeld University (2015-04-28).
• Bridging the Gap: Integrated Development of Linguistic Resources and Analyzers for NLP.
  • Johns Hopkins University CLSP (2014-04-02).
  • University of Toronto Computational Linguistics Meeting (2014-08-08).
  • University of Edinburgh ILCC Seminar (2014-10-24).
  • Bielefeld University (2015-04-27).
  • University of Copenhagen Centre for Language Technology (2015-04-30).
• Broad-coverage analysis of English MWEs: from annotation to sequence tagging. Poster at PARSEME 4th General Meeting (March 2015), Valleta, Malta.
• Lexical semantics with WordNet + Python. Python Linguistics Group, University of Pittsburgh (2013-10-21).
• Discriminative Lexical Semantic Segmentation with Gaps: Running the MWE Gamut.
  • Natural Language Processing course, CMU (2014-04-24).
  • Berkeley NLP Group (2013-09-04).
  • LTI Student Research Symposium (2013-08-21). Best Presentation Award
• Exploiting and expanding corpus resources for frame-semantic parsing. Presented at International FrameNet Workshop 2013.
• English Understanding: From Annotation to AMRs. ISI NLP Group (2012-08-28).
• Casting a wider ’Net: NLP for the Social Web. CMU Qatar Computer Science, Doha (2011-10-05).
• Introduction to Computational Linguistics and Language Technologies.
  • Introduction to Linguistics course, University of Pittsburgh (2010-04-15).
  • Introduction to Arabic Linguistics course, University of Pittsburgh (2012-04-11).
• English morphology in construction grammar. Poster at CSDL 2010, San Diego.
• Probabilistic frame-semantic parsing. ICSI, Berkeley (2010-02-05).

Service

Co-organizer: SemEval 2016 shared task on Detecting Minimal Semantic Units and their Meanings (with Dirk Hovy, Anders Johannsen, and Marine Carpuat)

Co-proposer: Theme session on Computational Aspects of Frames and Constructions for the International Conference on Construction Grammar 2016 (with Miriam R. L. Petruck)

Mentor: NAACL Student Research Workshop 2015

Reviewer for the journals Computational Linguistics, Transactions of the ACL, and Language Resources and Evaluation; and conferences/workshops including ACL, NAACL, EACL, EMNLP, COLING, CoNLL, ICML, and AAAI.

Area chair: Language Resources and Evaluation, ACL 2016 (with Nianwen Xue)

Invited panelist at the Linguistic Annotation Workshop, June 6, 2015 in Denver (topic: syntactic annotation of non-canonical language).

Invited facilitator at the FrameNet Workshop, September 9–13, 2013 in Berkeley.

At Edinburgh:

• Organizer: ILCC Research Tutorial and Hackathon (2015-05-08)
• Organizer: Arguments and Adjuncts Reading Group (Fall 2014)

At CMU:

• Organizer: Linguistics Reading Group
• Co-organizer: CL+NLP Lunch Seminar, LTI Colloquium Committee, Student Activities Committee
• Volunteer: North American Computational Linguistics Olympiad and International Linguistics Olympiad

Abstract Meaning Representation (AMR) design team, Summer 2012–present

Publications

Refereed Journal Articles

• Nathan Schneider, Emily Danchik, Chris Dyer, and Noah A. Smith (2014). Discriminative lexical semantic segmentation with gaps: running the MWE gamut. Transactions of the Association for Computational Linguistics. Presentation at ACL 2014.
• Dipanjan Das, Desai Chen, André F. T. Martins, Nathan Schneider, and Noah A. Smith (2014). Frame-semantic parsing. Computational Linguistics 40(1).

Reviews & Position Papers

• Nathan Schneider (2015). What I’ve learned about annotating informal text (and why you shouldn’t take my word for it). Proceedings of the Linguistic Annotation Workshop.
• Nathan Schneider and Reut Tsarfaty (2013). Design Patterns in Fluid Construction Grammar, Luc Steels (editor). Computational Linguistics 39(2).

Refereed Conference Papers

• Nathan Schneider and Noah A. Smith (2015). A corpus and model integrating multiword expressions and supersenses. Proceedings of NAACL-HLT.
• Meghana Kshirsagar, Sam Thomson, Nathan Schneider, Jaime Carbonell, Noah A. Smith, and Chris Dyer (2015). Frame-semantic role labeling with heterogeneous annotations. Proceedings of ACL-IJCNLP.
• Lizhen Qu, Gabriela Ferraro, Liyuan Zhou, Weiwei Hou, Nathan Schneider, and Timothy Baldwin (2015). Big data small data, in domain out-of domain, known word unknown word: the impact of word representations on sequence labelling tasks. Proceedings of CoNLL.
• Lingpeng Kong, Nathan Schneider, Swabha Swayamdipta, Archna Bhatia, Chris Dyer, and Noah A. Smith (2014). Dependency parsing for tweets. Proceedings of EMNLP.
• Archna Bhatia, Chu-Cheng Lin, Nathan Schneider, Yulia Tsvetkov, Fatima Talib Al-Raisi, Laleh Roostapour, Jordan Bender, Abhimanu Kumar, Lori Levin, Mandy Simons, and Chris Dyer (2014). Automatic classification of communicative functions of definiteness. Proceedings of COLING.
• Nathan Schneider, Spencer Onuffer, Nora Kazour, Emily Danchik, Michael T. Mordowanec, Henrietta Conrad, and Noah A. Smith (2014). Comprehensive annotation of multiword expressions in a social web corpus. Proceedings of LREC.
• Yulia Tsvetkov, Nathan Schneider, Dirk Hovy, Archna Bhatia, Manaal Faruqui, and Chris Dyer (2014). Augmenting English adjective senses with supersenses. Proceedings of LREC.
• Nathan Schneider, Behrang Mohit, Chris Dyer, Kemal Oflazer, and Noah A. Smith (2013). Supersense tagging for Arabic: the MT-in-the-middle attack. Proceedings of NAACL-HLT.
• Olutobi Owoputi, Brendan O’Connor, Chris Dyer, Kevin Gimpel, Nathan Schneider, and Noah A. Smith (2013). Improved part-of-speech tagging for online conversational text with word clusters. Proceedings of NAACL-HLT.
• Nathan Schneider, Behrang Mohit, Kemal Oflazer, and Noah A. Smith (2012). Coarse lexical semantic annotation with supersenses: an Arabic case study. Proceedings of ACL.
• Behrang Mohit, Nathan Schneider, Rishav Bhowmick, Kemal Oflazer, and Noah A. Smith (2012). Recall-oriented learning of named entities in Arabic Wikipedia. Proceedings of EACL.
• Kevin Gimpel, Nathan Schneider, Brendan O’Connor, Dipanjan Das, Daniel Mills, Jacob Eisenstein, Michael Heilman, Dani Yogatama, Jeffrey Flanigan, and Noah A. Smith (2011). Part-of-speech tagging for Twitter: annotation, features, and experiments. Proceedings of ACL-HLT.
• Dipanjan Das, Nathan Schneider, Desai Chen, and Noah A. Smith (2010). Probabilistic frame-semantic parsing. Proceedings of NAACL-HLT.
• Nathan Schneider (2010). Computational cognitive morphosemantics: modeling morphological compositionality in Hebrew verbs with Embodied Construction Grammar. Proceedings of BLS.

Refereed Workshop Papers

• Nathan Schneider, Vivek Srikumar, Jena D. Hwang, and Martha Palmer (2015). A hierarchy with, of, and for preposition supersenses. Proceedings of Linguistic Annotation Workshop.
• Sam Thomson, Brendan O’Connor, Jeffrey Flanigan, David Bamman, Jesse Dodge, Swabha Swayamdipta, Nathan Schneider, Chris Dyer, and Noah A. Smith (2014). CMU: Arc-Factored, Discriminative Semantic Dependency Parsing. Proceedings of SemEval (Task 8: Broad-Coverage Semantic Dependency Parsing).
• Nathan Schneider, Brendan O’Connor, Naomi Saphra, David Bamman, Manaal Faruqui, Noah A. Smith, Chris Dyer, and Jason Baldridge (2013). A framework for (under)specifying dependency syntax without overloading annotators. Proceedings of Linguistic Annotation Workshop.
• Laura Banarescu, Claire Bonial, Shu Cai, Madalina Georgescu, Kira Griffitt, Ulf Hermjakob, Kevin Knight, Philipp Koehn, Martha Palmer, and Nathan Schneider (2013). Abstract Meaning Representation for sembanking. Proceedings of Linguistic Annotation Workshop.
• Yulia Tsvetkov, Naama Twitto, Nathan Schneider, Noam Ordan, Manaal Faruqui, Victor Chahuneau, Shuly Wintner, and Chris Dyer (2013). Identifying the L1 of non-native writers: the CMU-Haifa system. Proceedings of the 8th Workshop on Innovative Use of NLP for Building Educational Applications.
• Desai Chen, Nathan Schneider, Dipanjan Das, and Noah A. Smith (2010). SEMAFOR: Frame argument resolution with log-linear models. Proceedings of SemEval (Task 10: Linking Events and their Participants in Discourse).

Reports

• Nathan Schneider, Rebecca Hwa, Philip Gianfortoni, Dipanjan Das, Michael Heilman, Alan W. Black, Frederick L. Crabbe, and Noah A. Smith (July 2010). Visualizing topical quotations over time to understand news discourse. Technical Report CMU-LTI-10-013.
• Dipanjan Das, Nathan Schneider, Desai Chen, and Noah A. Smith (April 2010). SEMAFOR 1.0: A probabilistic frame-semantic parser. Technical Report CMU-LTI-10-001.
• Reza Bosagh Zadeh and Nathan Schneider (December 2008). Unsupervised approaches to sequence tagging, morphology induction, and lexical resource acquisition. LS2 course literature review.

Technical and personal skills

• Programming languages used on a regular basis: Python (text processing and statistical modeling) and HTML/CSS/Javascript/PHP/MySQL (web development and user interfaces for annotation); also fluent in Java
• Open source software projects: in addition to sharing code from published research, contributions to NLTK (including the SemCor and FrameNet modules) and Zotero
• Languages: English (native); studied conversational Hebrew, Arabic, French, and German
• Music: classical violin