Sentence Alignment: Difference between revisions

From MT Talks
Jump to navigation Jump to search
No edit summary
No edit summary
Line 15: Line 15:
== Other Algorithms & Tools ==
== Other Algorithms & Tools ==


* A comparison and evaluation of various approaches to sentence alignment<ref name="rosen">Alexandr Rosen. ''[utkl.ff.cuni.cz/~rosen/public/slovko05.pdf In Search of the Best Method for Sentence Alignment in Parallel Texts]''</ref>
* A comparison and evaluation of various approaches to sentence alignment<ref name="rosen">Alexandr Rosen. ''[http://utkl.ff.cuni.cz/~rosen/public/slovko05.pdf In Search of the Best Method for Sentence Alignment in Parallel Texts]''</ref>
* Hunalign<ref name="hunalign">D. Varga, L. Németh, P. Halácsy, A. Kornai, V. Trón, V. Nagy. ''[http://www.kornai.com/Papers/ranlp05parallel.pdf Parallel corpora for medium density languages]''</ref>
* [http://mokk.bme.hu/en/resources/hunalign/ Hunalign]<ref name="hunalign">D. Varga, L. Németh, P. Halácsy, A. Kornai, V. Trón, V. Nagy. ''[http://www.kornai.com/Papers/ranlp05parallel.pdf Parallel corpora for medium density languages]''</ref>
* Gargantua<ref name="gargantua">Fabienne Braune, Alexander Fraser. ''[www.ims.uni-stuttgart.de/~fraser/pubs/braune_coling2010.pdf Improved unsupervised sentence alignment for symmetrical and asymmetrical parallel corpora]''</ref>
* [http://sourceforge.net/projects/gargantua/ Gargantua]<ref name="gargantua">Fabienne Braune, Alexander Fraser. ''[www.ims.uni-stuttgart.de/~fraser/pubs/braune_coling2010.pdf Improved unsupervised sentence alignment for symmetrical and asymmetrical parallel corpora]''</ref>
* Rico's aligner
* [https://github.com/rsennrich/bleualign Bleualign]<ref name="bleualign">Rico Sennrich, Martin Volk. ''[http://www.zora.uzh.ch/48036/7/Sennrich_Volk_2011-V.pdf Iterative, MT-based sentence alignment of parallel texts]''</ref>


== Exercises ==
== Exercises ==

Revision as of 10:33, 10 March 2015

Lecture 7: Sentence Alignment
Lecture video: web TODO
Youtube
Exercises: [TODO Gale & Church algorithm]

{{#ev:youtube|https://www.youtube.com/watch?v=7KmjaXjWNo8%7C800%7Ccenter}}


Gale & Church algorithm[1]

Other Algorithms & Tools

Exercises

  • [TODO Implement Gale & Church alignment algorithm]

References

  1. William Gale, Kenneth Church. A Program for Aligning Sentences in Bilingual Corpora
  2. Alexandr Rosen. In Search of the Best Method for Sentence Alignment in Parallel Texts
  3. D. Varga, L. Németh, P. Halácsy, A. Kornai, V. Trón, V. Nagy. Parallel corpora for medium density languages
  4. Fabienne Braune, Alexander Fraser. [www.ims.uni-stuttgart.de/~fraser/pubs/braune_coling2010.pdf Improved unsupervised sentence alignment for symmetrical and asymmetrical parallel corpora]
  5. Rico Sennrich, Martin Volk. Iterative, MT-based sentence alignment of parallel texts