Eric Davis Masters Student Carnegie Mellon Language Technologies Institute 2602 Newell-Simon Hall Pittsburgh, PA 15213-3891 phone: (412) 651-6887 e-mail: dhdavis+ at cs dot cmu dot edu Curriculum Vitae: CV This page best viewed with Mozilla Firefox Background    Research   Classes   Papers   Publications   Personal

Background

I studied Linguistics, Psychology, and Computing at UCLA and graduated in 2003. I focused mainly on syntax, language acquisition, and language processing. I worked with Professor Nina Hyams on young children's acquisition of negation. I also did research on the Tip of the Tongue phenomena with the Psychology Department. My final year, I worked on my senior thesis about the definite article in the context of American slang with Professor Pamela Munro. After graduation, I headed to Korea, where I taught English for almost two and a half years. My research interests include NLP, parsing, and Machine Translation.

Research

Fall 2006 - Summer 2007

I worked with Alon Lavie, Brian MacWhinney, and Shuly Wintner on the GRASP project. Our goal was to automatically annotate the CHILDES database (a large database of child-parent conversations) with grammatical relations, in order to support advanced corpus-based research of child language acquisition. We also simultaneously developed a grammar in HPSG to describe child language acquisition progressively.

My main contributions to the project were:

• Hand annotating data in the CHILDES database
• Testing and improving performance of the MEGRASP parser
• Helping improve the current set of GRs to accurately reflect data
• Aiding in development and testing of grammar

Here is a copy of our guide to the Grammatical Relations in the CHILDES database.

Fall 2007 - April 2008

I worked with Lori Levin and Teruko Mitamura on the IAMTC project. Our goal was to define annotation guidelines and annotate documents of interest to the intelligence community. We created guidelines for three topics: event coreference, social relationships, and committed belief. On this last topic, we worked jointly with Columbia University. After hand-annotation, we looked to develop tools to automatically annotate our relations.

My main contributions to the project were:

• Developing guidelines for Committed Belief
• Developing guidelines for coreference and social relations
• Creating flow charts to quickly and accurate define annotation process
• Hand annotating data in the corpus
• Aiding in development of tools to automatically annotate

Here is a copy of our Committed Belief Manual fo annotating belief in communication.

This is our Event Co-Reference Manual for annotating event co-reference in communication.

This is our Relations Manual for annotating entity relations in communication.

April 2008 - Present

I am working with Alon Lavie and Brian MacWhinney on the Spanish GRASP project. Our goal is to automatically annotate the Spanish CHILDES database (a large database of child-parent conversations) with grammatical relations, in order to support advanced corpus-based research of child language acquisition.

My main contributions to the project are:

• Hand annotating data in the CHILDES Spanish database
• Testing and improving performance of the MEGRASP parser
• Creating training materials for the MEGRASP parser
• Refining and updating a set of POS tags for Spanish
• Developing a set of GRs for Spanish

Classes

Fall 2006

• Algorithms for NLP
• Fundamental Data Structures and Algorithms

Spring 2007

• Language and Statistics
• Machine Translation
• NLP Lab (Finite State Machine Track)

Fall 2007

• Machine Learning
• Software Engineering for Information Technology

Spring 2008

• Information Retrieval
• Software Engineering for Information Technology II: Opinion Analysis
• Advanced Machine Translation Seminar

Papers

Fall 2003

• 'The' Paper: The Definite Article in American English Slang (with Pamela Munro)           'The' Paper.pdf

Spring 2007

• Korean Verbal Morphological Analyzer           NLP Lab Report.pdf
• Curious George Learns About Machine Translation           Korean Machine Translation.pdf
• Classifying Articles as Real or Fake           LS-report.pdf

Fall 2007

• Software Engineering Team Report           Team Report

Publications

Spring 2007

• Sagae, Kenji, Davis, Eric, Alon Lavie, et al: High-accuracy Annotation and Parsing of CHILDES Transcripts.           ACL Workshop.pdf

Personal

While in Korea, I met the love of my life, Julie. She is an English teacher in Korea. We have been dating for about 3 years now. We are engaged and will be married next year. She will be spending the year with me in Pittsburgh and studying at CCAC.

Naturally, I speak English, but I also speak three other languages to varying degrees of fluency: Spanish, German, and Korean. I have traveled throughout South America, Europe, and Asia. In high school, I went on a month-long exchange program to Uruguay and had the pleasure of visiting Iguazu Falls in Argentina and Brazil. My Junior year at UCLA, I studied abroad for 5 months in Bayreuth, Germany (town motto: "Even Germans have never heard of it!!!") While in Korea, I had the pleasure of traveling to Japan numerous times, as well as China, Indonesia, and Thailand.

I also enjoy being active. I swam and played tennis, soccer, and basketball as a kid and ran cross-country and track in high school. At UCLA, I got into triathlons and finished 3rd in my age group at the 2000 LA Triathlon. If I can find any free time these days, I enjoy golfing and swimming.