Re: [Moses-support] Language Model Training failed
Hi Janez, Seth syggested you the right fix I just checked the IRSTLM documentation http://sourceforge.net/apps/mediawiki/irstlm/index.php?title=Estimating_gigantic_models and the correct notation is reported there. Could you please tell me from where do you get the wrong information So that I correct it. Nicola (on behalf of IRSTLM development team) On Mar 5, 2014, at 1:36 AM, Seth Jarrett wrote: First four commands were executed successfuly. The last one failed. Here is the result after entering the following command line:zzz at zzz-laptop:~/lm$ ~/moses/irstlm/bin/compile-lm --text news-commentary-v8.fr-en.lm.en.gz news-commentary-v8.fr-en.arpa.en inpfile: news-commentary-v8.fr-en.arpa.enloading up to the LM level 1000 (if any) dub: 1000Failed to open news-commentary-v8.fr-en.arpa.en!zzz at zzz-laptop:~/lm$ Where we made a mistake? I see the xxx.arpa.en listed as input file. Shouldn't be the xxx.arpa.en file an output file?Best regards! I was having the same problem when following the steps in the baseline instructions but I was able to get it to work by adding yes after --text. Try this: ~/moses/irstlm/bin/compile-lm --text yes news-commentary-v8.fr-en.lm.en.gz news-commentary-v8.fr-en.arpa.en ___ Moses-support mailing list Moses-support@mit.edumailto:Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support ___ Moses-support mailing list Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support
Re: [Moses-support] Language Model Training failed
I just checked the IRSTLM documentation http://sourceforge.net/apps/mediawiki/irstlm/index.php?title=Estimating_gigantic_models and the correct notation is reported there. Could you please tell me from where do you get the wrong information So that I correct it. Nicola (on behalf of IRSTLM development team) Hi Nicola, The problem is in the instructions on the Moses/Baseline page in the IRSTLM section: http://www.statmt.org/moses/?n=Moses.Baseline#irstlm I found the correct notation using compile-lm --help so it looks like only the baseline page has this problem. But it's pretty important for beginners! Seth ___ Moses-support mailing list Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support
Re: [Moses-support] Language Model Training failed
Hi Nicola When I tried with irstlm 5.80.03, the version mentioned on the Moses baseline page (http://www.statmt.org/moses/?n=Moses.Baseline), it did not like the yes. Has there been a change in irstlm? I can check again. There has been some history with this argument. You can see in the wiki history of the Moses baseline page that the yes was added (because some users reported problems) then removed (because other users reported problems). Clarification of what works with what version of irstlm would be very useful, cheers - Barry On 05/03/14 08:51, Nicola Bertoldi wrote: Hi Janez, Seth syggested you the right fix I just checked the IRSTLM documentation http://sourceforge.net/apps/mediawiki/irstlm/index.php?title=Estimating_gigantic_models and the correct notation is reported there. Could you please tell me from where do you get the wrong information So that I correct it. Nicola (on behalf of IRSTLM development team) On Mar 5, 2014, at 1:36 AM, Seth Jarrett wrote: First four commands were executed successfuly. The last one failed. Here is the result after entering the following command line:zzz at zzz-laptop:~/lm$ ~/moses/irstlm/bin/compile-lm --text news-commentary-v8.fr-en.lm.en.gz news-commentary-v8.fr-en.arpa.en inpfile: news-commentary-v8.fr-en.arpa.enloading up to the LM level 1000 (if any) dub: 1000Failed to open news-commentary-v8.fr-en.arpa.en!zzz at zzz-laptop:~/lm$ Where we made a mistake? I see the xxx.arpa.en listed as input file. Shouldn't be the xxx.arpa.en file an output file?Best regards! I was having the same problem when following the steps in the baseline instructions but I was able to get it to work by adding yes after --text. Try this: ~/moses/irstlm/bin/compile-lm --text yes news-commentary-v8.fr-en.lm.en.gz news-commentary-v8.fr-en.arpa.en ___ Moses-support mailing list Moses-support@mit.edumailto:Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support ___ Moses-support mailing list Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support -- The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336. ___ Moses-support mailing list Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support
Re: [Moses-support] Language Model Training failed
Hi Janez In my opinion there are two things that need to be somehow described or corrected in the Moses baseline: 1. Notify the user about the location of the Giza++ utilities (mosesdecoder/tools or mosesdecoder/giza++) and need to rename the folders to the one used in command. The instructions already ask you to copy the GIZA++ utilities to the tools directory, you must have missed out that step. 2. Remove the last char in the command, listed in the baseline. The is correct, it runs the command in the background, which is why it returns instantly. This is quite a normal thing to do in a UNIX environment. cheers - Barry On 05/03/14 09:43, Janez Kadivec wrote: Hi, thank you for your help. The added yes parameter resolved the situation. We are following the Moses baseline, published in the official Moses web site: http://www.statmt.org/moses/?n=moses.baseline Please correct the last command in the Language Model Traning section. The command is marked with red color. mkdir ~/lm cd ~/lm ~/irstlm/bin/add-start-end.sh \ ~/corpus/news-commentary-v8.fr-en.true.en \ news-commentary-v8.fr-en.sb.en export IRSTLM=$HOME/irstlm; ~/irstlm/bin/build-lm.sh \ -i news-commentary-v8.fr-en.sb.en \ -t ./tmp -p -s improved-kneser-ney -o news-commentary-v8.fr-en.lm.en * ~/irstlm/bin/compile-lm --text news-commentary-v8.fr-en.lm.en.gz \ news-commentary-v8.fr-en.arpa.en* We followed the same baseline. In the Training the Translation System we found the next inconsistency: We installed the Moses and part of it was also Giza++ installed under the ...mosesdecoder\giza++1.0.7. We executed the following commands from the Training the Translation System section: mkdir ~/working cd ~/working nohup nice ~/mosesdecoder/scripts/training/train-model.perl -root-dir train \ -corpus ~/corpus/news-commentary-v8.fr-en.clean \ -f fr -e en -alignment grow-diag-final-and -reordering msd-bidirectional-fe \ -lm 0:3:$HOME/lm/news-commentary-v8.fr-en.blm.en:8 \ -external-bin-dir ~/mosesdecoder/tools training.out During the execution of the last command (marked with green color) here was an error saying that the mkcls utility is not found. It's not found because in the initial installation there is no tools subdirectory. We renamed the Giza++107 directory to tools. The command was executed instantly with no results. So we removed the last character from the command. It's working now for about half an hour. ;) In my opinion there are two things that need to be somehow described or corrected in the Moses baseline: 1. Notify the user about the location of the Giza++ utilities (mosesdecoder/tools or mosesdecoder/giza++) and need to rename the folders to the one used in command. 2. Remove the last char in the command, listed in the baseline. Have a nice rest of the day. Janez Seth syggested you the right fix I just checked the IRSTLM documentation http://sourceforge.net/apps/mediawiki/irstlm/index.php?title=Estimating_gigantic_models and the correct notation is reported there. Could you please tell me from where do you get the wrong information So that I correct it. Nicola (on behalf of IRSTLM development team) On Mar 5, 2014, at 1:36 AM, Seth Jarrett wrote: First four commands were executed successfuly. The last one failed. Here is the result after entering the following command line:zzz at zzz-laptop:~/lm$ ~/moses/irstlm/bin/compile-lm --text news-commentary-v8.fr-en.lm.en.gz news-commentary-v8.fr-en.arpa.en inpfile: news-commentary-v8.fr-en.arpa.enloading up to the LM level 1000 (if any) dub: 1000Failed to open news-commentary-v8.fr-en.arpa.en!zzz at zzz-laptop:~/lm$ Where we made a mistake? I see the xxx.arpa.en listed as input file. Shouldn't be the xxx.arpa.en file an output file?Best regards! I was having the same problem when following the steps in the baseline instructions but I was able to get it to work by adding yes after --text. Try this: ~/moses/irstlm/bin/compile-lm --text yes news-commentary-v8.fr-en.lm.en.gz news-commentary-v8.fr-en.arpa.en ___ Moses-support mailing list Moses-support@mit.edu mailto:Moses-support@mit.edumailto:Moses-support@mit.edu mailto:Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support Call Send SMS Add to Skype You'll need Skype CreditFree via Skype ___ Moses-support mailing list Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support -- The University of Edinburgh is a charitable body, registered in Scotland, with registration
Re: [Moses-support] Language Model Training failed
Hi, I'm a beginnner in Linux... so I like to see things happening in the foreground :) If there is no need to change the command... don't do that... ;) Obviously I overlooked and did not go through the section of copying the giza++ utilities to the tools directory. Thank you for your help. Janez On Wed, Mar 5, 2014 at 11:01 AM, Barry Haddow bhad...@staffmail.ed.ac.ukwrote: Hi Janez In my opinion there are two things that need to be somehow described or corrected in the Moses baseline: 1. Notify the user about the location of the Giza++ utilities (mosesdecoder/tools or mosesdecoder/giza++) and need to rename the folders to the one used in command. The instructions already ask you to copy the GIZA++ utilities to the tools directory, you must have missed out that step. 2. Remove the last char in the command, listed in the baseline. The is correct, it runs the command in the background, which is why it returns instantly. This is quite a normal thing to do in a UNIX environment. cheers - Barry On 05/03/14 09:43, Janez Kadivec wrote: Hi, thank you for your help. The added yes parameter resolved the situation. We are following the Moses baseline, published in the official Moses web site: http://www.statmt.org/moses/?n=moses.baseline Please correct the last command in the Language Model Traning section. The command is marked with red color. mkdir ~/lm cd ~/lm ~/irstlm/bin/add-start-end.sh \ ~/corpus/news-commentary-v8.fr-en.true.en \ news-commentary-v8.fr-en.sb.en export IRSTLM=$HOME/irstlm; ~/irstlm/bin/build-lm.sh \ -i news-commentary-v8.fr-en.sb.en \ -t ./tmp -p -s improved-kneser-ney -o news-commentary-v8.fr-en.lm.en * ~/irstlm/bin/compile-lm --text news-commentary-v8.fr-en.lm.en.gz \ news-commentary-v8.fr-en.arpa.en* We followed the same baseline. In the Training the Translation System we found the next inconsistency: We installed the Moses and part of it was also Giza++ installed under the ...mosesdecoder\giza++1.0.7. We executed the following commands from the Training the Translation System section: mkdir ~/working cd ~/working nohup nice ~/mosesdecoder/scripts/training/train-model.perl -root-dir train \ -corpus ~/corpus/news-commentary-v8.fr-en.clean \ -f fr -e en -alignment grow-diag-final-and -reordering msd-bidirectional-fe \ -lm 0:3:$HOME/lm/news-commentary-v8.fr-en.blm.en:8 \ -external-bin-dir ~/mosesdecoder/tools training.out During the execution of the last command (marked with green color) here was an error saying that the mkcls utility is not found. It's not found because in the initial installation there is no tools subdirectory. We renamed the Giza++107 directory to tools. The command was executed instantly with no results. So we removed the last character from the command. It's working now for about half an hour. ;) In my opinion there are two things that need to be somehow described or corrected in the Moses baseline: 1. Notify the user about the location of the Giza++ utilities (mosesdecoder/tools or mosesdecoder/giza++) and need to rename the folders to the one used in command. 2. Remove the last char in the command, listed in the baseline. Have a nice rest of the day. Janez Seth syggested you the right fix I just checked the IRSTLM documentation http://sourceforge.net/apps/mediawiki/irstlm/index.php? title=Estimating_gigantic_models and the correct notation is reported there. Could you please tell me from where do you get the wrong information So that I correct it. Nicola (on behalf of IRSTLM development team) On Mar 5, 2014, at 1:36 AM, Seth Jarrett wrote: First four commands were executed successfuly. The last one failed. Here is the result after entering the following command line:zzz at zzz-laptop:~/lm$ ~/moses/irstlm/bin/compile-lm --text news-commentary-v8.fr-en.lm.en.gz news-commentary-v8.fr-en.arpa.en inpfile: news-commentary-v8.fr-en.arpa.enloading up to the LM level 1000 (if any) dub: 1000Failed to open news-commentary-v8.fr-en.arpa.en!zzz at zzz-laptop:~/lm$ Where we made a mistake? I see the xxx.arpa.en listed as input file. Shouldn't be the xxx.arpa.en file an output file?Best regards! I was having the same problem when following the steps in the baseline instructions but I was able to get it to work by adding yes after --text. Try this: ~/moses/irstlm/bin/compile-lm --text yes news-commentary-v8.fr-en.lm.en.gz news-commentary-v8.fr-en.arpa.en ___ Moses-support mailing list Moses-support@mit.edu mailto:Moses-support@mit.edumailto:Moses-support@mit.edu mailto:Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support
Re: [Moses-support] Incorrectly formated moses.ini with feature-overwrite?
ah, i didn't know the mert-moses.pl script writes to the ini file with the values from --decoder-flags. I'm not gonna change mert-moses as it's likely break it. I could change how the decoder -feature-overwrite works. At the moment, it's -feature-overwrite 'TranslationModel0 table-limit=100' I can change it to -feature-overwrite TranslationModel0 table-limit 100 i.e. don't have quotes or the equal sign. This should work with mert-moses.pl. It will take some testing On 4 March 2014 23:28, Kenneth Heafield mo...@kheafield.com wrote: Dear Moses, As is the custom of Philipp's people, I ran $moses/scripts/training/mert-moses.pl $data/tuning/input.tc.* $data/tuning/reference.tc.* $moses/bin/moses $data/moses.ini --nbest 100 --working-dir $mert --decoder-flags -threads 32 -mp -search-algorithm 1 -cube-pruning-pop-limit 1000 -s 1000 -feature-overwrite 'TranslationModel0 table-limit=100' -max-trans-opt-per-coverage 100 -v 0 --rootdir $moses/scripts -mertdir $moses/bin --batch-mira --return-best-dev -maximum-iterations 25 --threads 32 --no-filter-phrase-table --continue That failed part way through (it completed 12 iterations) and I got desperate enough to pick the best iteration by BLEU e.g. mert/run09.moses.ini . This file contains, in part, the following: [feature-overwrite] 'TranslationModel0 table-limit=100' After editing the file to use test-set filtered evaluation set, I ran Moses and got this error: Exception: moses/StaticData.cpp:1153 in void Moses::StaticData::OverrideFeatures() threw util::Exception because `toks.size() = 1'. Incorrect format for feature override: table-limit=100' It seems mert-moses.pl is generating moses.ini files that the decoder is unwilling to accept. Kenneth ___ Moses-support mailing list Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support -- Hieu Hoang Research Associate University of Edinburgh http://www.hoang.co.uk/hieu ___ Moses-support mailing list Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support
[Moses-support] mgiza tools not found
Hello, I'm getting an error from train-model.perl. my command: train-model.perl -root-dir ~/0301 -corpus ~/0301/0102.clean -f es -e en -alignment grow-diag-final-and -reordering msd-bidirectional-fe -lm 0:3:/home/ubuntu/0301/0102.blm.en:8 --mgiza --mgiza-cpus 2 --parallel --external-bin-dir /home/ubuntu/mosesdecoder/tools/ error: ERROR: Cannot find mkcls, GIZA++/mgiza, snt2cooc.out/snt2cooc in /home/ubuntu/mosesdecoder/tools. You MUST specify the parameter -external-bin-dir at /home/ubuntu/mosesdecoder/scripts/training/train-model.perl line 347. contents of my external-bin-dir: ubuntu@ip-172-31-1-144:~/mosesdecoder/tools$ ls -l -rwxrwxr-x 1 ubuntu ubuntu 1198461 Mar 5 11:45 GIZA++ -rwxrwxrwx 1 ubuntu ubuntu1790 Mar 5 11:49 merge_alignment.py -rwxrwxr-x 1 ubuntu ubuntu 492028 Mar 5 11:45 mkcls -rwxrwxr-x 1 ubuntu ubuntu 386711 Mar 5 11:45 snt2cooc.out Thanks in advance! ___ Moses-support mailing list Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support
Re: [Moses-support] mgiza tools not found
Please disregard, I solved it. Seems that the manual doesn't mention I need a subdirerctory tools/mgiza. thanks, Viktor 2014-03-05 13:00 GMT+01:00 Viktor Pless viktor.pl...@gmail.com: Hello, I'm getting an error from train-model.perl. my command: train-model.perl -root-dir ~/0301 -corpus ~/0301/0102.clean -f es -e en -alignment grow-diag-final-and -reordering msd-bidirectional-fe -lm 0:3:/home/ubuntu/0301/0102.blm.en:8 --mgiza --mgiza-cpus 2 --parallel --external-bin-dir /home/ubuntu/mosesdecoder/tools/ error: ERROR: Cannot find mkcls, GIZA++/mgiza, snt2cooc.out/snt2cooc in /home/ubuntu/mosesdecoder/tools. You MUST specify the parameter -external-bin-dir at /home/ubuntu/mosesdecoder/scripts/training/train-model.perl line 347. contents of my external-bin-dir: ubuntu@ip-172-31-1-144:~/mosesdecoder/tools$ ls -l -rwxrwxr-x 1 ubuntu ubuntu 1198461 Mar 5 11:45 GIZA++ -rwxrwxrwx 1 ubuntu ubuntu1790 Mar 5 11:49 merge_alignment.py -rwxrwxr-x 1 ubuntu ubuntu 492028 Mar 5 11:45 mkcls -rwxrwxr-x 1 ubuntu ubuntu 386711 Mar 5 11:45 snt2cooc.out Thanks in advance! ___ Moses-support mailing list Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support
Re: [Moses-support] mgiza tools not found
Hi Viktor If you give the argument --mgiza to train-model.perl, then you need to make sure mgiza is in your tools directory. mgiza should not be a subdirectory, it should be a binary that you can get from here: http://www.kyloo.net/software/doku.php/mgiza:overview cheers - Barry On 05/03/14 12:30, Viktor Pless wrote: Please disregard, I solved it. Seems that the manual doesn't mention I need a subdirerctory tools/mgiza. thanks, Viktor 2014-03-05 13:00 GMT+01:00 Viktor Pless viktor.pl...@gmail.com mailto:viktor.pl...@gmail.com: Hello, I'm getting an error from train-model.perl. my command: train-model.perl -root-dir ~/0301 -corpus ~/0301/0102.clean -f es -e en -alignment grow-diag-final-and -reordering msd-bidirectional-fe -lm 0:3:/home/ubuntu/0301/0102.blm.en:8 --mgiza --mgiza-cpus 2 --parallel --external-bin-dir /home/ubuntu/mosesdecoder/tools/ error: ERROR: Cannot find mkcls, GIZA++/mgiza, snt2cooc.out/snt2cooc in /home/ubuntu/mosesdecoder/tools. You MUST specify the parameter -external-bin-dir at /home/ubuntu/mosesdecoder/scripts/training /train-model.perl line 347. contents of my external-bin-dir: ubuntu@ip-172-31-1-144:~/mosesdecoder/tools$ ls -l -rwxrwxr-x 1 ubuntu ubuntu 1198461 Mar 5 11:45 GIZA++ -rwxrwxrwx 1 ubuntu ubuntu1790 Mar 5 11:49 merge_alignment.py -rwxrwxr-x 1 ubuntu ubuntu 492028 Mar 5 11:45 mkcls -rwxrwxr-x 1 ubuntu ubuntu 386711 Mar 5 11:45 snt2cooc.out Thanks in advance! ___ Moses-support mailing list Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support -- The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336. ___ Moses-support mailing list Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support
Re: [Moses-support] mgiza tools not found
Ah I see. Thanks, Barry! 2014-03-05 13:42 GMT+01:00 Barry Haddow bhad...@staffmail.ed.ac.uk: Hi Viktor If you give the argument --mgiza to train-model.perl, then you need to make sure mgiza is in your tools directory. mgiza should not be a subdirectory, it should be a binary that you can get from here: http://www.kyloo.net/software/doku.php/mgiza:overview cheers - Barry On 05/03/14 12:30, Viktor Pless wrote: Please disregard, I solved it. Seems that the manual doesn't mention I need a subdirerctory tools/mgiza. thanks, Viktor 2014-03-05 13:00 GMT+01:00 Viktor Pless viktor.pl...@gmail.com mailto: viktor.pl...@gmail.com: Hello, I'm getting an error from train-model.perl. my command: train-model.perl -root-dir ~/0301 -corpus ~/0301/0102.clean -f es -e en -alignment grow-diag-final-and -reordering msd-bidirectional-fe -lm 0:3:/home/ubuntu/0301/0102.blm.en:8 --mgiza --mgiza-cpus 2 --parallel --external-bin-dir /home/ubuntu/mosesdecoder/tools/ error: ERROR: Cannot find mkcls, GIZA++/mgiza, snt2cooc.out/snt2cooc in /home/ubuntu/mosesdecoder/tools. You MUST specify the parameter -external-bin-dir at /home/ubuntu/mosesdecoder/scripts/training /train-model.perl line 347. contents of my external-bin-dir: ubuntu@ip-172-31-1-144:~/mosesdecoder/tools$ ls -l -rwxrwxr-x 1 ubuntu ubuntu 1198461 Mar 5 11:45 GIZA++ -rwxrwxrwx 1 ubuntu ubuntu1790 Mar 5 11:49 merge_alignment.py -rwxrwxr-x 1 ubuntu ubuntu 492028 Mar 5 11:45 mkcls -rwxrwxr-x 1 ubuntu ubuntu 386711 Mar 5 11:45 snt2cooc.out Thanks in advance! ___ Moses-support mailing list Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support -- The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336. ___ Moses-support mailing list Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support
Re: [Moses-support] phrase-extraction
If you mean a tool to create a corpus of aligned sentences, hunalign is suppose to be ok http://mokk.bme.hu/en/resources/hunalign/ If you mean a tool to create translation rules from source and target sentence with word alignments, then the extract and extract-rules programs in moses does this. They are in the bin/ directory once you have compiled Moses On 3 March 2014 16:12, Saeed Farzi saeedfa...@gmail.com wrote: Dear all, I need a tool for extracting phrases of a aligned sentence pairs. tnx in advance -- S.Farzi, Ph.D. Student Natural Language Processing Lab, School of Electrical and Computer Eng., Tehran University Tel: +9821-6111-9719 ___ Moses-support mailing list Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support -- Hieu Hoang Research Associate University of Edinburgh http://www.hoang.co.uk/hieu ___ Moses-support mailing list Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support
[Moses-support] TSD 2014 - Second Call for Papers
* TSD 2014 - SECOND CALL FOR PAPERS * Seventeenth International Conference on TEXT, SPEECH and DIALOGUE (TSD 2014) Brno, Czech Republic, 8-12 September 2014 http://www.tsdconference.org/ The conference is organized by the Faculty of Informatics, Masaryk University, Brno, and the Faculty of Applied Sciences, University of West Bohemia, Pilsen. The conference is supported by International Speech Communication Association. Venue: Brno, Czech Republic THE SUBMISSION DEADLINES: March 15 2014 Submission of abstracts March 22 2014 Submission of full papers Submission of abstract serves for better organization of the review process only - for the actual review a full paper submission is necessary. TSD SERIES TSD series evolved as a prime forum for interaction between researchers in both spoken and written language processing from all over the world. Proceedings of TSD form a book published by Springer-Verlag in their Lecture Notes in Artificial Intelligence (LNAI) series. TSD Proceedings are regularly indexed by Thomson Reuters Conference Proceedings Citation Index. Moreover, LNAI series are listed in all major citation databases such as DBLP, SCOPUS, EI, INSPEC or COMPENDEX. TOPICS Topics of the conference will include (but are not limited to): Corpora and Language Resources (monolingual, multilingual, text and spoken corpora, large web corpora, disambiguation, specialized lexicons, dictionaries) Speech Recognition (multilingual, continuous, emotional speech, handicapped speaker, out-of-vocabulary words, alternative way of feature extraction, new models for acoustic and language modelling) Tagging, Classification and Parsing of Text and Speech (morphological and syntactic analysis, synthesis and disambiguation, multilingual processing, sentiment analysis, credibility analysis, automatic text labeling, summarization, authorship attribution) Speech and Spoken Language Generation (multilingual, high fidelity speech synthesis, computer singing) Semantic Processing of Text and Speech (information extraction, information retrieval, data mining, semantic web, knowledge representation, inference, ontologies, sense disambiguation, plagiarism detection) Integrating Applications of Text and Speech Processing (machine translation, natural language understanding, question-answering strategies, assistive technologies) Automatic Dialogue Systems (self-learning, multilingual, question-answering systems, dialogue strategies, prosody in dialogues) Multimodal Techniques and Modelling (video processing, facial animation, visual speech synthesis, user modelling, emotions and personality modelling) Papers on processing of languages other than English are strongly encouraged. PROGRAM COMMITTEE Hynek Hermansky, USA (general chair) Eneko Agirre, Spain Genevieve Baudoin, France Paul Cook, Australia Jan Cernocky, Czech Republic Simon Dobrisek, Slovenia Karina Evgrafova, Russia Darja Fiser, Slovenia Radovan Garabik, Slovakia Alexander Gelbukh, Mexico Louise Guthrie, GB Jan Hajic, Czech Republic Eva Hajicova, Czech Republic Yannis Haralambous, France Ludwig Hitzenberger, Germany Jaroslava Hlavacova, Czech Republic Ales Horak, Czech Republic Eduard Hovy, USA Maria Khokhlova, Russia Daniil Kocharov, Russia Ivan Kopecek, Czech Republic Valia Kordoni, Germany Steven Krauwer, The Netherlands Siegfried Kunzmann, Germany Natalija Loukachevitch, Russia Vaclav Matousek, Czech Republic Diana McCarthy, United Kingdom France Mihelic, Slovenia Hermann Ney, Germany Elmar Noeth, Germany Karel Oliva, Czech Republic Karel Pala, Czech Republic Nikola Pavesic, Slovenia Fabio Pianesi, Italy Maciej Piasecki, Poland Adam Przepiorkowski, Poland Josef Psutka, Czech Republic James Pustejovsky, USA German Rigau, Spain Leon Rothkrantz, The Netherlands Anna Rumshisky, USA Milan Rusko, Slovakia Mykola Sazhok, Ukraine Pavel Skrelin, Russia Pavel Smrz, Czech Republic Petr Sojka, Czech Republic Stefan Steidl, Germany Georg Stemmer, Germany Marko Tadic, Croatia Tamas Varadi, Hungary Zygmunt Vetulani, Poland Pascal Wiggers, The Netherlands Yorick Wilks, GB Marcin Wolinski, Poland Victor Zakharov, Russia KEYNOTE SPEAKERS Ralph Grishman, New York University, USA Bernardo Magnini, FBK - Fondazione Bruno Kessler, Italy Salim Roukos, IBM, USA FORMAT OF THE CONFERENCE The conference program will include presentation of invited papers, oral presentations, and poster/demonstration sessions. Papers will be