Claire Cardie, Assistant Professor.
- 4124 Upson Hall
- Phone: 607-255-9206
- Fax : 607-255-4428
- Email: cardie@cs.cornell.edu
Click on these to see:
Although my research spans a number of subfields within artificial intelligence,
including machine learning, case-based reasoning, and cognitive
modeling, the focus of my research is in the area of natural
language understanding (NLP/NLU).
The NLP group at Cornell is primarily interested in investigating the use of machine
learning techniques as tools for guiding natural language system development and for
exploring the mechanisms that underly language acquisition. Our work focuses on two
related areas: (1) the design of user-trained systems that can efficiently and reliably
extract the important information from a document, and (2) the machine learning of natural
language.
- Information Extraction.
As part of Cornell's CSTR project, we are using information extraction techniques to
support content-based browsing of technical texts.
- The Kenmore Project.
The focus of the Kenmore project is on developing techniques to automate the knowledge
acquisition tasks that comprise the building of any NLP system. Very generally, Kenmore
acquires linguistic knowledge using a combination of symbolic machine learning
techniques and robust sentence analysis. It has been used with corpora from two
real-world domains to perform part-of-speech tagging, semantic feature tagging, and
concept activation and to find the antecedents of relative pronouns. In current work,
we are extending Kenmore to handle larger text corpora and additional disambiguation
tasks. In all of our work, we evaluate the language learning
components in the context of the larger NLP application in which it is
embedded. The goal of the project is to determine the conditions under which machine
learning techniques can be expected to offer a cost-effective approach to knowledge
acquisition for NLP systems.
- Embedded Machine Learning Systems for Natural Language Processing: A
General Framework,
C. Cardie. In Wermter, S. and Riloff, E.
and Scheler, Gabriele (eds.), Connectionist, Statistical and
Symbolic Approaches to Learning for Natural Language Processing,
Lecture Notes in Artificial Intelligence, 315-328, Springer,
1996. Originally presented at the Workshop on New Approaches to
Learning for Natural Language Processing, 14th International Joint
Conference on Artificial Intelligence (IJCAI-95), 119-126,
1995. AAAI Press.
- Chapter 1 (Introduction), Ph.D. Thesis,
C. Cardie. Domain-Specific Knowledge Acquisition for Conceptual Sentence Analysis,
Ph.D. Thesis, University of Massachusetts, Amherst, MA,
1994. Note that this file contains just the introductory chapter of the thesis.
- Using Cognitive Biases to Guide Feature Set Selection,
C. Cardie. Proceedings of the Fourteenth Annual Conference of the Cognitive
Science Society, 743-748, Bloomington, IN, Lawrence Erlbaum
Associates, and Working Notes of the AAAI Workshop on
Constraining Learning with Prior Knowledge, 11-18, San Jose, CA,
1992.
- Analyzing Research Papers Using Citation Sentences,
W. Lehnert, C. Cardie, and E. Riloff. Proceedings of the Twelfth Annual Conference of the Cognitive
Science Society, 511-518, Cambridge, MA, 1990. Lawrence Erlbaum
Associates.