The KIT translation systems for IWSLT 2015

In this paper, we present the KIT systems participating in the TED translation tasks of the IWSLT 2015 machine translation evaluation. We submitted phrase-based translation systems for three directions, namely English!German, German!English, and English!Vietnamese. For the official directions (English!German and German!English), we built systems both for the machine translation (MT) as well as the spoken language translation (SLT) tracks. This year we improved our systems’ performance over last year through n-best list rescoring using neural networkbased translation and language models and novel discriminative models based on different source-side features and classification methods. For the SLT tracks, we used a monolingual translation system to translate the lowercased ASR hypotheses with all punctuation stripped to truecased, punctuated output as a preprocessing step to our usual translation system. In addition to punctuation insertion, we also trained that system for sentence boundary insertion since the SLT’s data this year come with no sentence boundary.

[1]  Ewan Klein,et al.  Natural Language Processing with Python , 2009 .

[2]  Helmut Schmidt,et al.  Probabilistic part-of-speech tagging using decision trees , 1994 .

[3]  Jan Niehues,et al.  The Karlsruhe Institute for Technology Translation System for the ACL-WMT 2010 , 2010, WMT@ACL.

[4]  William D. Lewis,et al.  Intelligent Selection of Language Model Training Data , 2010, ACL.

[5]  Jan Niehues,et al.  Continuous space language models using restricted Boltzmann machines , 2012, IWSLT.

[6]  Philipp Koehn,et al.  Moses: Open Source Toolkit for Statistical Machine Translation , 2007, ACL.

[7]  Mona T. Diab,et al.  Second Generation AMIRA Tools for Arabic Processing : Fast and Robust Tokenization , POS tagging , and Base Phrase Chunking , 2009 .

[8]  Tie-Yan Liu,et al.  Learning to rank: from pairwise approach to listwise approach , 2007, ICML '07.

[9]  Andreas Stolcke,et al.  SRILM - an extensible language modeling toolkit , 2002, INTERSPEECH.

[10]  András Kornai,et al.  Parallel corpora for medium density languages , 2007 .

[11]  Preslav Nakov,et al.  Combining Word-Level and Character-Level Models for Machine Translation Between Closely-Related Languages , 2012, ACL.

[12]  Mauro Cettolo,et al.  WIT3: Web Inventory of Transcribed and Translated Talks , 2012, EAMT.

[13]  Jan Niehues,et al.  The Karlsruhe Institute of Technology Translation Systems for the WMT 2013 , 2012, WMT@NAACL-HLT.

[14]  Elena Deza,et al.  Dictionary of distances , 2006 .

[15]  Jan Niehues,et al.  Wider Context by Using Bilingual Language Models in Machine Translation , 2011, WMT@EMNLP.

[16]  Young-Suk Lee,et al.  Morphological Analysis for Statistical Machine Translation , 2004, NAACL.

[17]  Marcello Federico,et al.  Report on the 10th IWSLT evaluation campaign , 2013, IWSLT.

[18]  Jan Niehues,et al.  Discriminative Word Alignment via Alignment Matrix Modeling , 2008, WMT@ACL.

[19]  R. Stephenson.  A and V , 1962, The British journal of ophthalmology.

[20]  Franz Josef Och,et al.  An Efficient Method for Determining Bilingual Word Classes , 1999, EACL.

[21]  Jan Niehues,et al.  The KIT English-French translation systems for IWSLT 2011 , 2011, IWSLT.

[22]  A. Waibel,et al.  Rule-based preordering on multiple syntactic levels in statistical machine translation , 2014, IWSLT.

[23]  Holger Schwenk,et al.  Large, Pruned or Continuous Space Language Models on a GPU for Statistical Machine Translation , 2012, WLM@NAACL-HLT.

[24]  Philipp Koehn,et al.  Explorer Edinburgh System Description for the 2005 IWSLT Speech Translation Evaluation , 2005 .

[25]  S. Vogel,et al.  SMT decoder dissected: word reordering , 2003, International Conference on Natural Language Processing and Knowledge Engineering, 2003. Proceedings. 2003.

[26]  Ashish Vaswani,et al.  Decoding with Large-Scale Neural Language Models Improves Translation , 2013, EMNLP.

[27]  Jan Niehues,et al.  Segmentation and punctuation prediction in speech language translation using a monolingual translation system , 2012, IWSLT.

[28]  Harold W. Kuhn,et al.  The Hungarian method for the assignment problem , 1955, 50 Years of Integer Programming.

[29]  Hô Tuòng Vinh,et al.  A Hybrid Approach to Word Segmentation of Vietnamese Texts , 2008, LATA.

[30]  Roland Kuhn,et al.  Phrasetable Smoothing for Statistical Machine Translation , 2006, EMNLP.

[31]  A. Waibel,et al.  Detailed Analysis of Different Strategies for Phrase Table Adaptation in SMT , 2012, AMTA.

[32]  Sebastian Stüker,et al.  Overview of the IWSLT 2012 evaluation campaign , 2012, IWSLT.

[33]  Ashish Venugopal.  Training and Evaluating Error Minimization Rules for Statistical Machine Translation , 2005 .

[34]  Philipp Koehn,et al.  Empirical Methods for Compound Splitting , 2003, EACL.

[35]  Jan Niehues,et al.  Combining Word Reordering Methods on different Linguistic Abstraction Levels for Statistical Machine Translation , 2013, SSST@NAACL-HLT.

[36]  Jan Niehues,et al.  An MT Error-Driven Discriminative Word Lexicon using Sentence Structure Features , 2013, WMT@ACL.

[37]  Markus Freitag,et al.  Modeling punctuation prediction as machine translation , 2011, IWSLT.

[38]  Richard M. Schwartz,et al.  Fast and Robust Neural Network Joint Models for Statistical Machine Translation , 2014, ACL.

[39]  Geoffrey Zweig,et al.  Linguistic Regularities in Continuous Space Word Representations , 2013, NAACL.

[40]  Jan Niehues,et al.  A POS-Based Model for Long-Range Reorderings in SMT , 2009, WMT@EACL.

[41]  Alexandre Allauzen,et al.  Continuous Space Translation Models with Neural Networks , 2012, NAACL.

[42]  Christopher D. Manning,et al.  Parsing Three German Treebanks: Lexicalized and Unlexicalized Baselines , 2008 .

[43]  Alex Waibel,et al.  Combining Techniques from different NN-based Language Models for Machine Translation , 2014 .

[44]  Kenneth Heafield,et al.  KenLM: Faster and Smaller Language Model Queries , 2011, WMT@EMNLP.

[45]  Ben Taskar,et al.  An End-to-End Discriminative Approach to Machine Translation , 2006, ACL.

[46]  Stanley F. Chen,et al.  An empirical study of smoothing techniques for language modeling , 1999 .

[47]  Hermann Ney,et al.  A Systematic Comparison of Various Statistical Alignment Models , 2003, CL.

[48]  Jan Niehues,et al.  Parallel Phrase Scoring for Extra-large Corpora , 2012, Prague Bull. Math. Linguistics.

[49]  Hermann Ney,et al.  Extending Statistical Machine Translation with Discriminative and Trigger-Based Lexicon Models , 2009, EMNLP.

[50]  Helmut Schmid,et al.  Estimation of Conditional Probabilities With Decision Trees and an Application to Fine-Grained POS Tagging , 2008, COLING.

[51]  Nizar Habash,et al.  Permission is granted to quote short excerpts and to reproduce figures and tables from this report, provided that the source of such material is fully acknowledged. Arabic Preprocessing Schemes for Statistical Machine Translation , 2006 .

[52]  Dan Klein,et al.  Accurate Unlexicalized Parsing , 2003, ACL.

[53]  Alexandre Allauzen,et al.  Structured Output Layer neural network language model , 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).