Dr. Rada Mihalcea

The NewScientist article Sharing a joke could help man and robot interact said

A MAN walks into a bar: “Ouch!” You might not find it funny, but at least you got the joke. That’s more than can be said for computers, which, despite radical advances in artificial intelligence, remain notably devoid of a funny bone.
 
Previously AI researchers have tended not to try mimicking humor, largely because the human sense of humor is so subjective and complex, making it difficult to program.
 
Meanwhile Rada Mihalcea and colleagues at the University of North Texas in Denton have built a different kind of humor-spotting bot. Instead of working out why a sentence might be funny, it learns the frequencies of words that are found in jokes, and uses that to identify humor. “We got a lot of ‘can’t’, ‘don’t’, ‘drunk’ and ‘poor’,” Mihalcea says. “People like laughing about bad things.”

Rada Mihalcea, Ph.D. is President of SIGLEX and Assistant Professor of Computer Science and Engineering at the University of North Texas. She is on the Editorial Boards of Computational Linguistics, Journal of Interesting Negative Results in Natural Language Processing and Machine Learning, Journal of Natural Language Engineering and Language Resources and Evaluations. She is on the board of SIGNLL, and on the advising committee of Senseval/Semeval.
 
Rada’s research interests are in Natural Language Processing, Machine Learning, and Information Retrieval. Specifically, she is currently working on the following problems:

• Lexical Semantics (including: semantic similarity, word sense disambiguation, semantic parsing)
• Graph-based Algorithms for Natural Language Processing (with applications including: text summarization, word sense disambiguation, keyphrase extraction)
• Building and Exploiting Parallel Texts, Multilingual NLP
• Computational Humor
• Building Annotated Corpora with Volunteer Contributions over the Web
• Sentiment and Subjectivity Analysis

Her research projects are funded by the National Science Foundation, Google, the Texas Advanced Research Program, and ARDA-AQUAINT. They are:

• SenseLearner: tools for finding the meaning of all words in unrestricted text
• Teach-Computers: data collection with volunteer contributions over the Web
• TextRank: graph-based ranking algorithms for text processing
• Babylon: methods for building and exploiting parallel texts. Related resources for word/sentence alignment.
• Computational Humor: computational approaches for humor recognition and generation
• Sentiment and Subjectivity Analysis: recognizing private states such as opinions, emotions, speculations, and sentiments for use in NLP applications.

Rada authored Using Wikipedia for Automatic Word Sense Disambiguation, and coauthored Unsupervised Graph-based Word Sense Disambiguation Using Measures of Word Semantic Similarity, Random-Walk Term Weighting for Improved Text Classification, Learning Multilingual Subjective Language via Cross-Lingual Projections, Corpus-based and Knowledge-based Measures of Text Semantic Similarity, Word Alignment for Languages with Scarce Resources, and Exploiting Agreement and Disagreement of Human Annotators for Word Sense Disambiguation. Read her full list of publications!
 
Rada earned her Ph.D. at Southern Methodist in 2001. Download her SenseLearner: All-Words Word Sense Disambiguation Tool. Read Google Awards Grant to Rada Mihalcea.