Machine Translation and Morphologically-Rich Languages

Research Workshop of the Israel Science Foundation

University of Haifa, Israel

23-27 January 2011




Sunday 23 January


Kevin Knight: Integrated morphology for translation; presentation


Nachum Dershowitz: Using semantics in translation; presentation


Reshef Shilon: Machine translation between Hebrew and Arabic: needs, challenges and preliminary solutions.


Kfir Bar: Using verb paraphrases for Arabic-to-English example-based translation;  presentation


Raphael Cohen: Transliterated pairs acquisition in medical Hebrew;  presentation


Yoav Goldberg: Agreement matters: challenges of translating into a morphologically rich language, and the advantages of a syntax-based system;  presentation


Michael Elhadad: Topic models for morphologically rich languages and their usage to explore multilingual corpora; presentation


Monday 24 January


Lluís Màrquez: Automatic evaluation in machine translation: towards combined linguistically-motivated measures; presentation


Ido Dagan: Textual entailment inference in machine translation; presentation


Yulia Tsvetkov: Identification of multi-word expressions by combining multiple linguistic information sources; presentation


Reut Tsarfaty: Morphology, syntax, and what’s in between: reifying cross-linguistic variation through cross-linguistic parsing; presentation


Alexandru Ceausu: Rich morpho-syntactic descriptors for factored machine translation with highly inflected languages as target; presentation


Ondřej Bojar: Forms wanted: training SMT on monolingual data;  presentation


Chris Dyer: Integrating morphology in probabilistic translation models; presentation


Marcello Federico: Morphological processing and word reordering for statistical MT of highly inflected languages; presentation


Wednesday 26 January


Philipp Koehn: Factored models for morphology; presentation


Alexander Fraser: Morphological generation of German for SMT;  presentation


Gennadi Lembersky: Language models for machine translation: original vs. translated texts; presentation


Alex Rudnick: A resource-light approach to learning verb valencies; presentation


Igor Boguslavsky: Processing of Russian by the ETAP-3 linguistic processor; presentation


Raivis Skadiņs: Improving SMT with morphology knowledge for Baltic languages; presentation


Alon Lavie: The impact of Arabic morphological segmentation on broad-scale phrase-based SMT; presentation


Sergei Nirenburg: Morphological aspects of computer-driven elicitation of  knowledge about any language; presentation


Thursday 27 January


Kemal Oflazer: Syntax-to-morphology mapping in factored SMT; presentation


Coşkun Mermer: Unsupervised Turksih morphological segmentation for statistical machine translation; presentation


Tsuyoshi Okita: MWE-sensitive word alignment in factored translation model; presentation


Jason Eisner and Markus Dreyer: A non-parametric Bayesian approach to inflectional morphology; presentation by Jason Eisner; presentation by Markus Dreyer


Papers accepted but not presented


Guy De Pauw: Towards English-Swahili machine translation.


Vishal Goyal: Hindi to Punjabi machine translation system.


Alicia Pérez: Steps taken in Spanish-Basque speech translation using stochastic finite-state transducers.