Elamur Research
☰
home / topics / Machine translation

Machine translation

326 paper cards from the Research library · page 1 of 4

What it is

Machine translation, MT for short, translates text from one language to another by program. The first systems were rules written by hand: dictionaries and grammars of transfer from one language's structure to another's, or an interlingua that belongs to no language. Statistical systems then learned translation tables from aligned texts, and neural networks now translate whole sentences at once.

Translation is hard because languages cut the world differently: words have no exact match, word order changes, and style matters as much as meaning. Systems are measured with people's judgments and with automatic scores such as BLEU that compare the output with human translations.

How Mova does it

Mova translates without a neural network: a text is read down its language's stack into a tree, frames and a world, then into a meta-world that belongs to no language, and written out by the target language's encoder with the target author's delta. The test is byte for byte on verse-aligned Bibles, and what is lost is measured in bits at every stage.

The papers (326)

Cards with a measured or kept idea first, then by citations.

Pages: 1 · 2 · 3 · 4

  1. Bleu: a Method for Automatic Evaluation of Machine Translation — Kishore Papineni, Salim Roukos, Todd Ward, Wei-Jing Zhu, 2002 · 21238 citations
  2. METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments — Satanjeev Banerjee, Alon Lavie, 2005 · 3458 citations
  3. A Study of Translation Edit Rate with Targeted Human Annotation — Matthew Snover, Bonnie Dorr, Rich Schwartz, Linnea Micciulla et al., 2006 · 2310 citations
  4. A Call for Clarity in Reporting BLEU Scores — Matt Post, 2018 · 2025 citations
  5. Hierarchical Phrase-Based Translation — David Chiang, 2007 · 1144 citations
  6. A Hierarchical Phrase-Based Model for Statistical Machine Translation — David Chiang, 2005 · 1137 citations
  7. Abstract Meaning Representation for Sembanking — Laura Banarescu, Claire Bonial, Shu Cai, Madalina Georgescu et al., 2013 · 1062 citations
  8. chrF: character n-gram F-score for automatic MT evaluation — Maja Popović, 2015 · 1011 citations
  9. Stochastic Inversion Transduction Grammars and Bilingual Parsing of Parallel Corpora — Dekai Wu, 1997 · 841 citations
  10. A Syntax-based Statistical Translation Model — Kenji Yamada, Kevin Knight, 2001 · 728 citations
  11. COMET: A Neural Framework for MT Evaluation — Ricardo Rei, Craig Stewart, Ana C Farinha, Alon Lavie, 2020 · 617 citations
  12. PPDB: The Paraphrase Database — Juri Ganitkevitch, Benjamin Van Durme, Chris Callison-Burch, 2013 · 613 citations
  13. Style Transfer from Non-Parallel Text by Cross-Alignment — Tianxiao Shen, Tao Lei, Regina Barzilay, Tommi Jaakkola, 2017 · 584 citations
  14. Paraphrasing with Bilingual Parallel Corpora — Colin Bannard, Chris Callison-Burch, 2005 · 533 citations
  15. Optimizing Statistical Machine Translation for Text Simplification — Wei Xu, Courtney Napoles, Ellie Pavlick, Quanze Chen et al., 2016 · 521 citations
  16. Extracting Paraphrases from a Parallel Corpus — Regina Barzilay, Kathleen R. McKeown, 2001 · 470 citations
  17. What's in a translation rule? — Michel Galley, Mark Hopkins, Kevin Knight, Daniel Marcu, 2004 · 460 citations
  18. Learning to Paraphrase: An Unsupervised Approach Using Multiple-Sequence Alignment — Regina Barzilay, Lillian Lee, 2003 · 426 citations
  19. Scalable Inference and Training of Context-Rich Syntactic Translation Models — Michel Galley, Jonathan Graehl, Kevin Knight, Daniel Marcu et al., 2006 · 414 citations
  20. Dependency Treelet Translation: Syntactically Informed Phrasal SMT — Chris Quirk, Arul Menezes, Colin Cherry, 2005 · 379 citations
  21. A Structured Review of the Validity of BLEU — Ehud Reiter, 2018 · 376 citations
  22. The WebNLG Challenge: Generating Text from RDF Data — Claire Gardent, Anastasia Shimorina, Shashi Narayan, Laura Perez-Beltrachini, 2017 · 342 citations
  23. Dear Sir or Madam, May I Introduce the GYAFC Dataset: Corpus, Benchmarks and Metrics for Formality Style Transfer — Sudha Rao, Joel Tetreault, 2018 · 321 citations
  24. A Monolingual Tree-based Translation Model for Sentence Simplification — Zhemin Zhu, Delphine Bernhard, Iryna Gurevych, 2010 · 319 citations
  25. Tree-to-String Alignment Template for Statistical Machine Translation — Yang Liu, Qun Liu, Shouxun Lin, 2006 · 318 citations
  26. Monolingual Machine Translation for Paraphrase Generation — Chris Quirk, Chris Brockett, William Dolan, 2004 · 307 citations
  27. Generating Phrasal and Sentential Paraphrases: A Survey of Data-Driven Methods — Nitin Madnani, Bonnie J. Dorr, 2010 · 298 citations
  28. chrF++: words helping character n-grams — Maja Popović, 2017 · 279 citations
  29. Experts, Errors, and Context: A Large-Scale Study of Human Evaluation for Machine Translation — Markus Freitag, George Foster, David Grangier, Viresh Ratnakar et al., 2021 · 265 citations
  30. Error Analysis of Statistical Machine Translation Output — David Vilar, Jia Xu, Luis Fernando D'Haro, Hermann Ney, 2006 · 257 citations
  31. PPDB 2.0: Better paraphrase ranking, fine-grained entailment relations, word embeddings, and style classification — Ellie Pavlick, Pushpendre Rastogi, Juri Ganitkevitch, Benjamin Van Durme et al., 2015 · 256 citations
  32. Neural AMR: Sequence-to-Sequence Models for Parsing and Generation — Ioannis Konstas, Srinivasan Iyer, Mark Yatskar, Yejin Choi et al., 2017 · 252 citations
  33. A New String-to-Dependency Machine Translation Algorithm with a Target Dependency Language Model — Libin Shen, Jinxi Xu, Ralph Weischedel, 2008 · 250 citations
  34. Learning Non-Isomorphic Tree Mappings for Machine Translation — Jason Eisner, 2003 · 239 citations
  35. Machine Translation Divergences: A Formal Description and Proposed Solution — Bonnie J. Dorr, 1994 · 238 citations
  36. Sentence Simplification by Monolingual Machine Translation — Sander Wubben, Antal van den Bosch, Emiel Krahmer, 2012 · 230 citations
  37. Learning to Simplify Sentences with Quasi-Synchronous Grammar and Integer Programming — Kristian Woodsend, Mirella Lapata, 2011 · 204 citations
  38. A Fast and Portable Realizer for Text Generation Systems — Benoit Lavoie, Owen Rainbow, 1997 · 200 citations
  39. Machine Translation Using Probabilistic Synchronous Dependency Insertion Grammars — Yuan Ding, Martha Palmer, 2005 · 197 citations
  40. Reformulating Unsupervised Style Transfer as Paraphrase Generation — Kalpesh Krishna, John Wieting, Mohit Iyyer, 2020 · 185 citations
  41. Tangled up in BLEU: Reevaluating the Evaluation of Automatic Machine Translation Evaluation Metrics — Nitika Mathur, Timothy Baldwin, Trevor Cohn, 2020 · 182 citations
  42. Statistical Syntax-Directed Translation with Extended Domain of Locality — Liang Huang, Kevin Knight, Aravind Joshi, 2006 · 172 citations
  43. Syntactic Features for Evaluation of Machine Translation — Ding Liu, Daniel Gildea, 2005 · 161 citations
  44. A Challenge Set Approach to Evaluating Machine Translation — Pierre Isabelle, Colin Cherry, George Foster, 2017 · 158 citations
  45. Shakespearizing Modern Language Using Copy-Enriched Sequence to Sequence Models — Harsh Jhamtani, Varun Gangal, Eduard Hovy, Eric Nyberg, 2017 · 154 citations
  46. Forest-Based Translation — Haitao Mi, Liang Huang, Qun Liu, 2008 · 146 citations
  47. An Empirical Analysis of Formality in Online Communication — Ellie Pavlick, Joel Tetreault, 2016 · 136 citations
  48. A Survey of Machine Translation: Its History, Current Status and Future Prospects — Jonathan Slocum, 1985 · 130 citations
  49. CharacTer: Translation Edit Rate on Character Level — Weiyue Wang, Jan-Thorsten Peter, Hendrik Rosendahl, Hermann Ney, 2016 · 129 citations
  50. Chart Generation — Martin Kay, 1996 · 127 citations
  51. Semantics-Based Machine Translation with Hyperedge Replacement Grammars — Bevan Jones, Jacob Andreas, Daniel Bauer, Karl Moritz Hermann et al., 2012 · 115 citations
  52. Learning to Translate with Source and Target Syntax — David Chiang, 2010 · 109 citations
  53. The First Surface Realisation Shared Task: Overview and Evaluation Results — Anja Belz, Michael White, Dominic Espinosa, Eric Kow et al., 2011 · 104 citations
  54. Translation by Structural Correspondences — Ronald M. Kaplan, Klaus Netter, Jurgen Wedekind, Annie Zaenen, 1989 · 99 citations
  55. Generation from Abstract Meaning Representation using Tree Transducers — Jeffrey Flanigan, Chris Dyer, Noah A. Smith, Jaime Carbonell, 2016 · 96 citations
  56. Generation by Inverting a Semantic Parser that Uses Statistical Machine Translation — Yuk Wah Wong, Raymond Mooney, 2007 · 92 citations
  57. Shake-and-Bake Translation — P. Whitelock, 1992 · 92 citations
  58. MEANT: An inexpensive, high-accuracy, semi-automatic metric for evaluating translation utility based on semantic roles — Chi-kiu Lo, Dekai Wu, 2011 · 87 citations
  59. Aligning English Strings with Abstract Meaning Representation Graphs — Nima Pourdamghani, Yang Gao, Ulf Hermjakob, Kevin Knight, 2014 · 86 citations
  60. Semantic Neural Machine Translation Using AMR — Linfeng Song, Daniel Gildea, Yue Zhang, Zhiguo Wang et al., 2019 · 85 citations
  61. Paraphrasing for Style — Wei Xu, Alan Ritter, Bill Dolan, Ralph Grishman et al., 2012 · 85 citations
  62. Hybrid text simplification using synchronous dependency grammars with hand-written and automatically harvested rules — Advaith Siddharthan, Angrosh Mandya, 2014 · 82 citations
  63. AMR-to-text Generation with Synchronous Node Replacement Grammar — Linfeng Song, Xiaochang Peng, Yue Zhang, Zhiguo Wang et al., 2017 · 78 citations
  64. Semantic Structural Evaluation for Text Simplification — Elior Sulem, Omri Abend, Ari Rappoport, 2018 · 76 citations
  65. Simple and Effective Text Simplification Using Semantic and Neural Methods — Elior Sulem, Omri Abend, Ari Rappoport, 2018 · 72 citations
  66. Generating English from Abstract Meaning Representations — Nima Pourdamghani, Kevin Knight, Ulf Hermjakob, 2016 · 66 citations
  67. Using Test Suites in Evaluation of Machine Translation Systems — Margaret King, Kirsten Falkedal, 1990 · 64 citations
  68. Not an Interlingua, But Close: Comparison of English AMRs to Chinese and Czech — Nianwen Xue, Ondřej Bojar, Jan Hajič, Martha Palmer et al., 2014 · 61 citations
  69. Design of LMT: A Prolog-Based Machine Translation System — Michael C. McCord, 1989 · 57 citations
  70. Broad Coverage Multilingual Deep Sentence Generation with a Stochastic Multi-Level Realizer — Bernd Bohnet, Leo Wanner, Simon Mille, Alicia Burga, 2010 · 56 citations
  71. Blast: A Tool for Error Analysis of Machine Translation Output — Sara Stymne, 2011 · 55 citations
  72. Squib: Expressive Power of Abstract Meaning Representations — Johan Bos, 2016 · 54 citations
  73. Text Simplification using Typed Dependencies: A Comparision of the Robustness of Different Generation Strategies — Advaith Siddharthan, 2011 · 52 citations
  74. MEANT 2.0: Accurate semantic MT evaluation for any output language — Chi-kiu Lo, 2017 · 51 citations
  75. Learning How to Simplify From Explicit Labeling of Complex-Simplified Text Pairs — Fernando Alva-Manchego, Joachim Bingel, Gustavo Paetzold, Carolina Scarton et al., 2017 · 50 citations
  76. A Large-Scale Comparison of Historical Text Normalization Systems — Marcel Bollmann, 2019 · 49 citations
  77. Unsupervised Sentence Simplification Using Deep Semantics — Shashi Narayan, Claire Gardent, 2016 · 47 citations
  78. The First Multilingual Surface Realisation Shared Task (SR'18): Overview and Evaluation Results — Simon Mille, Anja Belz, Bernd Bohnet, Yvette Graham et al., 2018 · 46 citations
  79. chrF deconstructed: beta parameters and n-gram weights — Maja Popović, 2016 · 46 citations
  80. CILI: the Collaborative Interlingual Index — Francis Bond, Piek Vossen, John P. McCrae, Christiane Fellbaum, 2016 · 46 citations
  81. Towards broad coverage surface realization with CCG — Michael White, Rajakrishnan Rajkumar, Scott Martin, 2007 · 46 citations
  82. Pragmatically Informative Text Generation — Sheng Shen, Daniel Fried, Jacob Andreas, Dan Klein, 2019 · 45 citations
  83. Solving Thematic Divergences in Machine Translation — Bonnie Dorr, 1990 · 44 citations
  84. Translation by Quasi Logical Form Transfer — Hiyan Alshawi, David Carter, Manny Rayner, Bjorn Gamback, 1991 · 43 citations
  85. Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer — Juncen Li, Robin Jia, He He, Percy Liang, 2018 · 41 citations
  86. Translation Divergences in Chinese–English Machine Translation: An Empirical Investigation — Dun Deng, Nianwen Xue, 2017 · 39 citations
  87. Evaluating prose style transfer with the Bible — Keith Carlson, Allen Riddell, Daniel Rockmore, 2017 · 38 citations
  88. Inferring Shallow-Transfer Machine Translation Rules from Small Parallel Corpora — Felipe Sanchez-Martinez, Mikel L. Forcada, 2009 · 38 citations
  89. Morpho-syntactic Information for Automatic Error Analysis of Statistical Machine Translation Output — Maja Popović, Adrià de Gispert, Deepa Gupta, Patrik Lambert et al., 2006 · 38 citations
  90. Normalisation of Historical Text Using Context-Sensitive Weighted Levenshtein Distance and Compound Splitting — Eva Pettersson, Beáta Megyesi, Joakim Nivre, 2013 · 35 citations
  91. Linguistic realisation as machine translation: Comparing different MT models for AMR-to-text generation — Thiago Castro Ferreira, Iacer Calixto, Sander Wubben, Emiel Krahmer, 2017 · 34 citations
  92. Transition-Based Syntactic Linearization — Yijia Liu, Yue Zhang, Wanxiang Che, Bing Qin, 2015 · 34 citations
  93. Rule-Based Normalization of Historical Texts — Marcel Bollmann, Florian Petran, Stefanie Dipper, 2011 · 33 citations
  94. Machine Translation without a source text — Harold L. Somers, Jun-ichi Tsujii, Danny Jones, 1990 · 33 citations
  95. HUME: Human UCCA-Based Evaluation of Machine Translation — Alexandra Birch, Omri Abend, Ondřej Bojar, Barry Haddow, 2016 · 32 citations
  96. SEM-I Rational MT: Enriching Deep Grammars with a Semantic Interface for Scalable Machine Translation — Dan Flickinger, Jan Tore Lønning, Helge Dyvik, Stephan Oepen et al., 2005 · 31 citations
  97. Phrase-Based and Deep Syntactic English-to-Czech Statistical Machine Translation — Ondřej Bojar, Jan Hajič, 2008 · 28 citations
  98. Generation-Heavy Hybrid Machine Translation — Nizar Habash, 2002 · 28 citations
  99. Annotation of Tense and Aspect Semantics for Sentential AMR — Lucia Donatelli, Michael Regan, William Croft, Nathan Schneider, 2018 · 26 citations
  100. Approximating an Interlingua in a Principled Way — Eduard Hovy, Sergei Nirenburg, 1992 · 26 citations

Pages: 1 · 2 · 3 · 4

More papers in the library (168)

The most cited first. All 168 →