International Workshop on

Using Linguistic Information

for Hybrid Machine Translation

LIHMT

 

Shared Task on

Applying Machine Learning

Techniques to Optimise the

Division of Labour in Hybrid

Machine Translation

Barcelona

November 2011

 

 

 


LIHMT 2011

International Workshop on

Using Linguistic Information

for Hybrid Machine Translation

18th November 2011

Universitat Politècnica de Catalunya

Barcelona

 

Contents

 

Introductions, programme, and About the OpenMT-2 project

 

Rich morphology and what can we expect from hybrid approaches to MT [abstract].

Ondřej Bojar

 

Statistical MT with syntax and morphology: challenges and some solutions [abstract]

    Alon Lavie

 

Linguistic indicators for quality estimation of machine translation [abstract]

    Lucia Specia

 

Improved statistical machine translation using multiword expressions.

    Dhouha Bouamor, Nasredine Semmar, and Pierre Zweigenbaum

 

VERTa: exploring a multidimensional linguistically-motivated metric.

    Elisabet Comelles, Jordi Atserias, Victoria Arranz, Irene Castellón, and Olivier Hamon

 

Using Apertium linguistic data for tokenization to improve Moses SMT performance.

Santiago Cortés Vaíllo and Sergio Ortiz Rojas

 

Reordering by parsing

    Jakob Elming and Martin Haulrich

 

Comparing corpus-based MT approaches using restricted resources.

    Monica Gavrila and Natalia Elita

 

Deep evaluation of hybrid architectures: simple metrics correlated with human judgments

    Gorka Labaka, Arantza Díaz de Ilarraza, Cristina España-Bonet, Lluís Màrquez and Kepa Sarsola

 

A radically simple, effective annotation and alignment methodology for semantic frame based SMT and MT evaluation.

    Chi-kiu Lo and Dekai Wu

 

Word translation disambiguation without parallel texts.

    Erwin Marsi, André Lynum, Lars Bungum, and Björn Gambäck

 

A new hybrid machine translation approach using cross-language information retrieval and only target text corpora.

    Nasredine Semmar and Dhouha Bouamor

 

 

ML4HMT

Shared Task on

Applying Machine Learning

Techniques to Optimise the

Division of Labour in Hybrid

Machine Translation

19th November

Barcelona Media

Barcelona

 

Contents

 

Introduction, programme and about META-NET

 

Machine translation system combination with MANY for ML4HMT

  LoïcBarrault & Patrik Lambert

 

DCU confusion network-based system combination for ML4HMT

  Tsuyoshi Okita and Josef van Genabith

 

DFKI system combination with sentence ranking at ML4HMT-2011.

Eleftherios Avramidis

 

DFKI system combination using syntactic information at ML4HMT-2011

  Christian Federmann, Sabine Hunsicker, Yu Chen, and Rui Wang

 

Results from the ML4HMT shared task on applying machine learning techniques to optimise the division of labour in hybrid MT

  Christian Federmann