Irene Langkilde
Also known as Irene Langkilde-Geary
Irene Langkilde is a researcher in natural language generation who worked on generating sentences with corpus-based statistics. She earned a Ph.D. at the University of Southern California in 2002 under Kevin Knight, with whom she published "Generation that Exploits Corpus-Based Statistical Knowledge" at ACL in 1998. In November 2001, she described the Nitrogen sentence generator, a system of about 200,000 words and concepts, at a University of Maryland symposium. By 2005, she was an assistant professor at Brigham Young University and a member of the SIGGEN board, and in 2007 and 2009 she published work on constraint programming for probabilistic syntactic processing. In 2023, the Association for Computational Linguistics gave the 1998 paper its Test-of-Time Paper Award.
Timeline
-
1998
Two papers with Kevin Knight
In August 1998, she and Kevin Knight publish "Generation that Exploits Corpus-Based Statistical Knowledge" in the proceedings of the 36th Annual Meeting of the Association for Computational Linguistics in Montreal. Their paper "The Practical Value of N-Grams Is in Generation" appears in the proceedings of the Natural Language Generation workshop in Niagara-on-the-Lake, Ontario, in August 1998.
-
2000–2001
Forest-based statistical sentence generation
She publishes "Forest-Based Statistical Sentence Generation" at the first meeting of the North American Chapter of the Association for Computational Linguistics in 2000. In November 2001, she gives a talk titled "Statistical Sentence Generation" at a University of Maryland symposium on academic careers in computer science, where she describes Nitrogen, a sentence generator of about 200,000 words and concepts.
-
2002
Ph.D. under Kevin Knight
She earns a Ph.D. from the University of Southern California in 2002 with Kevin Knight as advisor, writing the dissertation "Automatic Sentence Generation Using a Hybrid Statistical Model of Lexical Collocations and Syntactic Relations". In July 2002, she publishes "An Empirical Verification of Coverage and Correctness for a General-Purpose Sentence Generator" at the International Natural Language Generation Conference in Harriman, New York.
-
By 2005
Assistant professor at BYU
By 2005, she is an assistant professor at Brigham Young University and one of four new members elected to the board of SIGGEN, the special interest group on natural language generation.
-
2006
A Penn Treebank dependency corpus
In 2006, she and Justin Betteridge publish "A Factored Functional Dependency Transformation of the English Penn Treebank for Probabilistic Surface Generation" at LREC 2006, describing a featurized functional dependency corpus derived from the Penn Treebank. Each word in the corpus carries over three dozen features that describe the functional syntactic structure of a sentence.
-
2007
ASGRE realizer and concurrent constraint programming
In September 2007, she publishes "Declarative syntactic processing of natural language using concurrent constraint programming and probabilistic dependency modeling" at the Workshop on Using Corpora for Natural Language Generation in Copenhagen, and in 2007 she writes the template-based realizer used for the ASGRE 2007 challenge, listed under Brighton University.
-
June 2009
Constraint programming for syntactic processing
In June 2009, she publishes "A Constraint Programming Approach to Probabilistic Syntactic Processing" at the Workshop on Integer Linear Programming for Natural Language Processing in Boulder, Colorado.
-
2023
ACL Test-of-Time Paper Award
In 2023, her 1998 paper with Kevin Knight, "Generation that Exploits Corpus-Based Statistical Knowledge", wins the ACL Test-of-Time Paper Award, shared with Hinrich Schütze's 1998 paper on word sense discrimination. The winners are announced at ACL 2023 in July 2023.
Career
- Brigham Young UniversityAssistant Professor
Education
- 2002University of Southern CaliforniaPh.D.
Sources and credits
Photo: We have no published photo of Irene Langkilde yet. Send us a free-licensed photo.
- Generation that Exploits Corpus-Based Statistical Knowledge - ACL Anthology
- The Practical Value of N-Grams Is in Generation - ACL Anthology
- Forest-Based Statistical Sentence Generation - ACL Anthology
- Langkilde-Geary: Statistical Sentence Generation (talk abstract)
- Research, Careers, and Computer Science: A Maryland Symposium
- Irene Langkilde - The Mathematics Genealogy Project
- Alumni - Artificial Intelligence
- An Empirical Verification of Coverage and Correctness for a General-Purpose Sentence Generator - ACL Anthology
- SIGGEN: Newsletter Archive - ACL Wiki
- Irene Langkilde - ACL Anthology
- OSU-GP: Attribute Selection using Genetic Programming
- Declarative syntactic processing of natural language using concurrent constraint programming and probabilistic dependency modeling - ACL Anthology
- A Constraint Programming Approach to Probabilistic Syntactic Processing - ACL Anthology
- ACL Test-of-Time Papers Award Recipients - Admin Wiki
- Announcement of the 2023 ACL Test-of-Time Paper Award | ACL Member Portal

