Nina Wacholder is co-director, with Mark Aakhus, of SALTS, the Laboratory for the Study of Applied Language Technology and Society. She is also the director of the Geraldine R. Dodge Poetry Festival Archive Project; Rutgers students and recent alumni manage the process and get experience in digital library creation of a unique, high quality resource.
City University of New York Graduate Center
M.A., Library Science
B.A., Classical Languages
Nina Wacholder’s research interests lie at the intersection of information science, computer science, and linguistics. At a theoretical level, her goal is to understand the impact of properties of human language such as ambiguity and irregularity on the exchange of information among people and between people and computers. At the applied level, her research focuses on using computer technology to improve people’s access to information stored in the form of language.
Current projects include the study of argument mining and argumentation, methodologies for studying human ability to recognize subtle linguistic phenomena and using knowledge about human language behavior to train automatically developed language models; assessment of the quality of index terms as used in electronic indexes and browsing systems, impact of readability of consumer health information on low literacy adults; and development of a theory of query term formulation in the information access process. She has also published on the evaluation of question answering systems, identification of proper names, and anatomical ontologies.
Centers, Labs, Working Groups, and Clusters
Funding to design Dodge Poetry Festival archive and populate with metadata from 2012, 2014 and 2016 festivals, Geraldine M. Dodge Foundation, September 2012 - August 2017
Google Research Award, Why users don’t take query suggestions: The impact of semantic and visual processing on search engine interaction, with Catherine L. Smith, 2009-2010
National Science Foundation, A better book viewer: Reading a million books, with Michael Lesk, 2004-2007
HITIQA (High Intensive Question Answering), with Tomek Strzalkowski (SUNY Albany) and Paul Kantor (Rutgers). Funded by the Advanced Research and Development Activity (ARDA) Advanced Question and Answering for Intelligence (AQUAINT) Program, May 2004-June 2005
Impact of school libraries on student learning. Project Director: Ross Todd, with Carol Kuhlthau and Nina Wacholder. Funded by Institute of Museum and Library Services (IMLS), 2004-2006
Muresan, Smaranda, Roberto-Gonzalez Ibanez, Debanjan Ghosh & Nina Wacholder. (2016). Identification of nonliteral language in social media: A case study on sarcasm. Journal of the Association for Information Science and Technology. Retrieved from http://onlinelibrary.wiley.com/doi/10.1002/asi.23624/abstract
Wacholder, Nina, Muresan, Smaranda, Ghosh, Debanjan, & Aakhus, Mark (2014). Annotating Multiparty Discourse: Challenges for Agreement Metrics. In Proceedings of Linguistic Annotation Workshop (LAW) VIII (p. 120). Baltimore, MD: ACL.
Ghosh, Debanjan, Muresan, Smaranda, Wacholder, Nina, Aakhus, Mark & Mitsui, Matthew. (2014). Analyzing argumentative discourse units in online interactions. In Proceedings of the First Workshop on Argumentation Mining (pp. 39–48). Dublin, Ireland: ACL.
Aakhus, Mark, Muresan, Smaranda & Wacholder, Nina. (2013). Integrating natural language processing and pragmatic argumentation theories for argumentation support. OSSA Conference Archive, Paper 1.
González-Ibánez, R., Smaranda Muresan, & Nina Wacholder. (2011). Identifying sarcasm in Twitter: A closer look. Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, 581–586.
Awards & Recognitions
Nina Wacholder, Inventor. Method and system for identifying significant topics of a document. Patent number 6,167,368. (2000)
Yael Ravin, Misook Choi, and Nina Wacholder, Inventors. Processing names in a text. Patent number 5,819,265. (1998)
Roy Byrd, Yael Ravin, and Nina Wacholder, Inventors. System and method for using canonical forms to develop a dictionary of names in a text. Patent number 5,832,480. (1998)