Jeffrey C. Micher
Ph.D. student in the Language Technologies Institute
School of Computer Science
Carnegie Mellon University
Ph.D. Thesis Proposal
Addressing Challenges of Machine Translation of Inuit Languages
Resources
A corpus of morphologically analyzed Inuktitut words lives here
Publications
2019
Jeffrey Micher, 2019, "Bootstrapping a Neural Morphological Generator from Morphological Analyzer Output for Inuktitut," Proceedings of the Workshop on Computational Methods for Endangered Languages: Vol. 2, Article 7. pdf
2018
Jeffrey C. Micher, 2018, Provenance and Processing of an Inuktitut-English Parallel Corpus Part 1: Inuktitut Data Preparation and Factored Data Format, Technical Note (ARL-TN-0923) Army Research Laboratory, Adelphi, MD. pdf
Jeffrey C. Micher, 2018, Addressing Challenges of Machine Translation of Inuit Languages Technical Note (ARL-TN-0924), Army Research Laboratory, Adelphi, MD. pdf
Jeffrey C. Micher, 2018, "Using the Nunavut Hansard Data for Experiments In Morphological Analysis and Machine Translation," Proceedings Proceedings of the Workshop on Computational Modeling of Polysynthetic Languages, Association for Computational Linguistics, Santa Fe, New Mexico, USA, pp 65-72. pdf
Judith Klavans, John Morgan, Stephen Larocca, Jeffrey Micher, Clare R. Voss, 2018. Challenges in Speech Recognition and Translation of High-Value Low-Density Polysynthetic Languages. AMTA (2) 2018: 283-293 pdf
2017
Jeffrey C. Micher, 2017, "Improving Coverage of an Inuktitut Morphological Analyzer Using a Segmental Recurrent Neural Network," Proceedings of the 2nd Workshop on the Use of Computational Methods in the Study of Endangered Languages, Association for Computational Linguistics, Honolulu, Hawaii. pdf
2012
Jeffrey C. Micher, 2012, Improving Domain-specific Machine Translation by Constraining the Language Model, Army Research Laboratory Technical Note, ARL-TN-0492. pdf
Jeffrey C. Micher, 2012, A Method for Correcting Broken Hyphenations in Noisy English Text, Army Research Laboratory Technical Note, ARL-TN-0481. pdf
2009
Jeffrey C. Micher, 2009, Adapting an Arabic Morphological Analyzer to Serve Word Lookup for Military Tasks, Army Research Laboratory Technical Report, ARL-TR-4945. pdf
2008
Clare R Voss, Matthew Aguirre, Jeffrey Micher, Richard Chang, Jamal Laoudi, Reginald Hobbs, 2008: Boosting performance of weak MT engines automatically: using MT output to align segments and build statistical post-editors, EAMT Hamburg, Germany, 2008. pdf
Jeffrey Micher and Clare Voss, 2008: "Buckwalter-based Lookup Tool as Language Resource for Arabic Language Learners" in Software Engineering, Testing, and Quality Assurance for Natural Language Processing, ACL-HLT Workshop Proceedings, 2008, Columbus, OH. pdf
Nyberg, Mitamura, Svoboda, Ko, Baker, and Micher, 2003: "An Integrated System for Source Language Checking, Analysis and Term Management", Proceedings of the Ninth MT Summit, September 2003, New Orleans pdf
1994
Micher, Jeffrey & Bruce Baker, 1994: Translation Problems of Terse Messages in Voice Output Communication Aids, Proceedings, Rehabilitation Engineering Society of North America (RESNA), Nashville TN
Brueziere, Gilles & Jeffrey Micher, 1994: The Development of a Representation of French Grammar, Proceedings, International Society for Augmentative and Alternative Communication (ISAAC), Maastricht, Netherlands
SG Thomason, D Berney, G Coelho, J Micher, D Everett, 1994, "Montana Salish root classes: Evidence from the 19th-century Jesuit dictionary," 29th International Conference on Salish and Neighboring Languages, pp. 288-312. pdf
Interests
Languages
I'm an incurable polyglot. Some of the languages I've studied:
- French: fluent; two years in highschool, French Major at University of Pittsburgh, 2 years living in France (Sept 1988-July 1990), various trips for my work with Semantic Compaction Systems
- German: intermediate level, conversational; four years highschool, misc. college courses, semester in Freiburg, summer as work study student in Cologne, various trips for my work with Semantic Compaction Systems
- Italian: intermediate level, conversational; minor at University of Pittsburgh, a few trips to Italy for work with Semantic Compaction Systems, developed Unity product for Semantic Compaction Systems with our Italian distributor
- Spanish: intermediate level, converstaional; One year college, travel in Spain for my work with Semantic Compaction Systems
- Portuguese: basic level; developed Unity product for Semantic Compaction Systems with our Portuguese distributor.
- Russian: basic level; one year in college
- Dutch: basic level, developed Unity product for Semantic Compaction Systems with our Dutch distributor
- Danish: basic level, developed Unity product for Semantic Compaction Systems with our Danish distributor
- Sanskrit: introductory reading level; one semester of Sanskrit in college
- Latin: introductory reading level; self-study
- Arabic: basic level; private tutoring for 90 hours
- Japanese: very basic level; self-study
- Modern Greek: basic conversational; self-study and some travel in Greece
- Inuktitut: knowledge of grammar; self-study and dissertation work
- Esperanto: knowledge of grammar and some vocabulary, self-study
- Slovio: I don't know this one, but I'm curious
Currently learning Slovak, with a private tutor and classes at University of Pittsburgh. My goal is to acquire conversational and reading skills for travel to Slovakia and Family History research
Since learning I have Manx ancestry, learning Manx is on my to do list.
Some links:
Rock Climbing
Gardening
Family History: