Publications
Filter:
Book
2009
Beyond Words and Phrases: A Unified Theory of Predicate Composition
Karine Megerdoomian
Complex predicates, Syntax-semantics
This volume presents a computational model of predicate composition that derives the distinct properties of "words" and "phrases" within a single component of grammar and its interface conditions, thus providing an insight into the interaction between morphology and syntax. Discover what this means for Persian and multilingual, low‑resource NLP.
Presentation
2009
Heritage Persian Characteristics and Needs
Karine Megerdoomian
Persian language teaching, Heritage speakers
The talk presents an overview of the linguistic and functional competence of Heritage and L2 speakers or Persian, based on recent research in the field, and shows that they have different characteristics. Discover what this means for Persian and multilingual, low‑resource NLP.
Technical Report
2009
On the IC Standard for Persian: Commentary on the Transcription Standard for Personal Names
Karine Megerdoomian
Surveys & evaluations
No abstract available. Learn what the authors found and why it matters.
Presentation
2009
Unclassified AFPAK Resources for Linguists
Karine Megerdoomian
Surveys & evaluations
List of language resources, such as corpora and analysis tools, for the languages of the AFPAK (Afghanistan-Pakistan) region. Learn what the authors found and why it matters.
Presentation
2009
D-Linked Wh-Phrases and Focus-Fronting in Persian
Shadi Ganjavi and Karin eMegerdoomian
Syntax-semantics
Languages differ on their typology as wh-movement, wh-in situ or focus-fronting language. Discover what this means for Persian and multilingual, low‑resource NLP.
Proceedings Article
2009
Automated Metrics for Speech Translation
Sherri Condon, Mark Arehart, Christy Doran, Dan Parvaz, John Aberdeen, Karine Megerdoomian, and Beatrice Oshika
Surveys & evaluations
In this paper, we describe automated measures used to evaluate machine translation quality in the Defense Advanced Research Projects Agency. Learn what the authors found and why it matters.
Technical Report
2009
The Structure of Afghan Names
Karine Megerdoomian
General AI
This report provides a description of the structure of Afghan names. Learn what the authors found and why it matters.
Technical Report
2009
TRANSTAC Transcription Guidelines for English/Dari
Karine Megerdoomian
Persian NLP
This report provides guidelines for transcribing Dari, as part of the NIST evaluation project speech translation in real-world tactical situations (TRANSTAC). Read for methods, evaluations, and why the findings matter for scalable AI systems.
Presentation
2009
MITRE Infrastructure and Evaluation for Identity Resolution Technology
Keith J. Miller, Elizabeth Schroeder, Sarah McLeod, Azar Ulrich, Karine Megerdoomian, James Finley, Gail Hamilton, Andre Milota, Ken Samuel, Sherri Condon and Mark Arehart
Surveys & evaluations
Across the government, analysts must search multiple data sources in order to create a composite view of information about a person. Read for methods, evaluations, and why the findings matter for scalable AI systems.
Journal Article
2009
Telicity in Persian Complex Predicates
Karine Megerdoomian
Complex predicates
In their study of complex predicates in Persian, Folli, Harley and Karimi (2005) propose that the nonverbal component (NV) is the sole determiner of telicity in the complex verbal construction. Discover what this means for Persian and multilingual, low‑resource NLP.
Technical Report
2008
Analysis of Farsi Weblogs
Karine Megerdoomian (with Tim Allison and Zohreh Nazeri)
Social media analytics, Persian NLP
The survey of the literature on Persian blogs presents the state of the Iranian Blogosphere (in 2008) and provides a review of the research and publications on the topic: Research on Persian blogs has mainly centered around a socio-political study of this new medium, and. Discover what this means for Persian and multilingual, low‑resource NLP.
Technical Report
2008
ARGUS Search and Stemming
Karine Megerdoomian
General AI
Information retrieval systems often use stemming, i. Discover what this means for Persian and multilingual, low‑resource NLP.