Thanks, Hieu. I will try out your solution later. Guchun
On 20 January 2012 14:11, <[email protected]> wrote: > Send Moses-support mailing list submissions to > [email protected] > > To subscribe or unsubscribe via the World Wide Web, visit > http://mailman.mit.edu/mailman/listinfo/moses-support > or, via email, send a message with subject or body 'help' to > [email protected] > > You can reach the person managing the list at > [email protected] > > When replying, please edit your Subject line so it is more specific > than "Re: Contents of Moses-support digest..." > > > Today's Topics: > > 1. Re: Incremental training (Hieu Hoang) > 2. EAMT 2012 - The 16th Annual Conference of the European > Association for Machine Translation - 2nd CFP (Lucia Specia) > 3. Re: Incremental training (Guchun Zhang) > > > ---------------------------------------------------------------------- > > Message: 1 > Date: Fri, 20 Jan 2012 19:41:03 +0700 > From: Hieu Hoang <[email protected]> > Subject: Re: [Moses-support] Incremental training > To: [email protected] > Message-ID: <[email protected]> > Content-Type: text/plain; charset="iso-8859-1" > > unfortunately, you can only set those arguments by changing the code in > the training script > train-model.perl > line 970 and 971 > > set them both to 0 > > On 20/01/2012 10:26, Qin Gao wrote: > > These are lexical translation and distortion models produced by > > previous training, and can be produced by removing -nodump and > > -onlyaldumps from giza options in moses training scripts. > > > > For documentation of giza and mgiza parameters, you can refer to > > > > http://geek.kyloo.net/software/doku.php/mgiza:configure > > > > Best, > > --Q > > > > > > On Thu, Jan 19, 2012 at 9:10 PM, Philipp Koehn <[email protected] > > <mailto:[email protected]>> wrote: > > > > Hi, > > > > these are paths to the model files produced > > for the original (not-updated) model. > > > > -phi > > > > On Thu, Jan 19, 2012 at 9:36 AM, Guchun Zhang <[email protected] > > <mailto:[email protected]>> wrote: > > > > Hi, > > > > I am trying out incremental training. I am stuck in the Update > > and Compute Alignments stage. In the sample config file for > > GIZA++, I am not quite sure what are the following parameters > > > > oldTrPrbs: <path-to-original-thmm> (old translation > > probabilities?) > > oldAlPrbs: <path-to-original-hhmm> (old alignment probabilities?) > > > > and where are the files they ask for? > > > > Many thanks, > > > > Guchun > > > > _______________________________________________ > > Moses-support mailing list > > [email protected] <mailto:[email protected]> > > http://mailman.mit.edu/mailman/listinfo/moses-support > > > > > > > > _______________________________________________ > > Moses-support mailing list > > [email protected] <mailto:[email protected]> > > http://mailman.mit.edu/mailman/listinfo/moses-support > > > > > > > > > > _______________________________________________ > > Moses-support mailing list > > [email protected] > > http://mailman.mit.edu/mailman/listinfo/moses-support > -------------- next part -------------- > An HTML attachment was scrubbed... > URL: > http://mailman.mit.edu/mailman/private/moses-support/attachments/20120120/55325bad/attachment-0001.htm > > ------------------------------ > > Message: 2 > Date: Fri, 20 Jan 2012 13:31:59 +0000 > From: Lucia Specia <[email protected]> > Subject: [Moses-support] EAMT 2012 - The 16th Annual Conference of the > European Association for Machine Translation - 2nd CFP > To: [email protected], [email protected], [email protected], > [email protected], [email protected] > Message-ID: > <CAALeUxyaiF13ME=pCR7SRL91kqCa8Ay+fvHA8bpVLymgFuDX=g...@mail.gmail.com > > > Content-Type: text/plain; charset=UTF-8 > > EAMT 2012 - The 16th Annual Conference of the European Association for > Machine Translation > > Fondazione Bruno Kessler (FBK) > Trento, Italy > 28-30 May 2012 > http://eamt2012.fbk.eu/ > > The European Association for Machine Translation (EAMT) is pleased to > announce that the 16th Annual Conference of the European Association > for Machine Translation will be held in Trento, Italy, 28-30 May 2012. > The venue of the conference is the Fondazione Bruno Kessler (FBK), at > the Center for Scientific and Technological Research. > > The EAMT invites everyone interested in machine translation and > translation-related tools and resources to participate in this > conference - developers, researchers, users, professional translators, > managers, marketing experts: anyone who has a stake in the vision of > an information world in which language issues become transparent to > the information consumer. We especially invite users from government > and the translation industry to share their experiences, researchers > to describe the state of the art and demonstrate their cutting-edge > results, researchers and developers looking towards new capabilities, > and visionaries to describe the future. > > ?------------------------------ ?What is new? > ?------------------------------ > > -- EAMT is growing, receiving more and more submissions every year. In > order to keep to the single track format - which makes EAMT events > very inclusive in nature - we are extending the duration of the > conference to from 2 to 2 and a half days. > > -- In order to particularly encourage submissions for the users? > track, we have created a new submission type: short papers for > oral/poster presentation: 2-4 pages. > > -- In order to encourage participation from developers/industry, we > have introduced a technology showcase, where people can demonstrate > their products. Submissions for this track require just a 1-page > abstract. > > ?------------------------------ Scope ?------------------------------ > > We expect to receive papers in two categories: > > (R) Research papers: Long-paper submissions (8 pages) are invited for > reports of significant research results in any aspect of machine > translation and related areas. Such reports should include a > substantial evaluation component. Contributions are welcome on all > topics in the area of Machine Translation or translation-related > technologies, including: > > * MT methodologies and techniques > * Speech translation: speech to text, speech to speech > * Translation aids (translation memory, terminology databases, etc.) > * Translation environments (workflow, support tools, conversion tools > for lexica, etc.) > * Practical MT systems (MT for professionals, MT for multilingual > eCommerce, MT for localization, etc.) > * MT in multilingual public service (eGovernment etc.) > * MT for the web > * MT embedded in other services > * MT evaluation techniques and evaluation results > * Dictionaries and lexica for MT > * Text and speech corpora for MT > * Standards in text and lexicon encoding for MT > * Human factors in MT and user interfaces > * Related multilingual technologies (natural language generation, > information retrieval, text categorization, text summarization, > information extraction, etc.) > > Papers should describe original work. They should emphasize completed > work rather than intended work, and should indicate clearly the state > of completion of the reported results. Where appropriate, concrete > evaluation results should be included. > > (U) User studies: Short-paper submissions (2-4 pages) are invited for > reports on users' experiences with MT, in business, government, or > NGOs. Contributions are welcome on: > > * Use of MT to provide localization of data-driven, dynamic, or > user-specific information > * Use of MT to reduce localization effort (time, cost) > * ?Use of MT in collaborative projects and social networking > * ?Ways in which MT can be used to increase the scope of globalization > projects > * ?Managing change when implementing MT systems. Challenges (IT, > personnel, implementation) > * ?Integrating MT and computer-assisted translation into a translation > production workflow > * Implementing open- source MT in the corporation: challenges when > taking pilot results into full deployment (support, resources, > infrastructure, advance customisation, system maintenance) > * Evaluation of MT in a real-world setting: metrics > * Post-editing strategies: guidelines/support for translators/LSPs > * Portability of MT systems across languages and domains > > Papers should highlight problems and solutions and not merely describe > MT integration process or project settings. For user papers produced > by academics, we require co-authorship with the actual users. > > Additionally, we welcome 1-page abstracts on: > > (P) Project/Product description: Submissions are invited to report > new, interesting: > > * Tools for machine translation, computer aided translation, and the > like (including commercial products and open source software). The > authors should be ready to present the tools in the form of demos or > posters during the conference. > * ?Research projects related to machine translation. The authors > should be ready to present the projects in the form of posters during > the conference. This follows on from the successful ?project villages? > held at the last two EAMT conferences. > > ?------------------------------ Programme ------------------------------ > > The programme will include invited talks, oral presentations and > poster sessions. Accepted long papers may be assigned to an oral or > poster session, but no differentiation will be made in the conference > proceedings. > Important Dates > > ?------------------------------ Important Dates > ------------------------------ > > * 15 February 2012 ? SUBMISSION DEADLINE > * 2 Apr 2012 ? Notification to authors > * 22 Apr 2012 ? Deadline for camera-ready copy > * 22 Apr 2012 ? Deadline for early-bird registration > * 28-30 May 2012 ? Conference > > Please visit the conference web pages (http://eamt2012.fbk.eu/) for > the most up-to-date information about the calendar, the call for > papers and formatting requirements, the programme, invited speakers, > related conference activities, the venue, travel and registration. > > ?------------------------------ Submissions ------------------------------ > > Submissions will be judged on correctness, originality, technical > strength, significance and relevance to the conference, and potential > interest to all attendees. They should mostly contain new material > that has not been presented at any other meeting with publicly > available proceedings. Papers that are being submitted in parallel to > other conferences or workshops and papers that contain significant > overlap with previously published work must indicate this on the title > page. > > EAMT 2012 will use electronic submission through the EasyChair > conference tool. To submit a paper, go to the submission website at: > http://www.easychair.org/conferences/?conf=eamt2012 and follow the > instructions. > > Papers should be anonymised (no authors, affiliations or addresses, > and no explicit self-reference), be no longer than 8 pages (A4 size) > for research papers, and no longer than 4 pages (A4 size) for user > papers, all in PDF format. Papers must conform to the format defined > by the EAMT templates available at the conference website > (http://eamt2012.fbk.eu/). Project/software descriptions do not need > to be anonymised. > > If you encounter any problem regarding submission, please do not > hesitate to contact the programme co-chairs. For all other queries > (e.g. visas, accommodation, payments) please contact the local > organisers. > > ---------------------------- Conference Organisers > --------------------------- > > Conference Chair > > Marcello Federico (FBK-irst, Italy) > > Programme Co-chairs > Lucia Specia - Research programme chair (University of Sheffield, UK) > Andy Way - User programme chair (Applied Language Solutions, UK) > > Local Organization Chair > Mauro Cettolo (FBK-irst, Italy) > > ---------------------------- Programme Committee > ---------------------------- > > Research track: > > Wilker Aziz (University of Wolverhampton, UK) > Nicola Bertoldi (Fondazione Bruno Kessler, Italy) > Alexandra Birch (University of Edinburgh, UK) > Herv? Blanchon (l'Universit? Pierre Mend?s - Grenoble 2, France) > Ondrej ?Bojar ?(Charles University, Prague) > Antal van den Bosch (Universiteit van Tilburg, Netherlands) > Bill ?Byrne (Cambridge University, UK) > Nicola Cancedda (Xerox Research Centre, France) > Michael Carl (IAI Saarbr?cken, Germany) > Helena Caseli (Universidade Federal de S?o Carlos, Brazil) > Marta Costa-juss? (Barcelona Media, Spain) > Jinhua Du (Xi'an University of Technology, China) > Marc Dymetman (Xerox Research Centre, France) > Andreas Eisele (European Commission, Luxembourg) > Mikel Forcada (Universitat d'Alacant) > Declan Groves (Dublin City University, Ireland) > Barry Haddow (University of Edinburgh, UK) > Yifan He (Dublin City University, Ireland) > Jie Jiang (Applied Language Solutions, UK) > Patrik Lambert (Universite? du Maine, France) > Alon Lavie (Carnegie-Mellon University, USA) > Yanjun Ma (Dublin City University, Ireland) > Pavel Pecina (Dublin City University, Ireland) > Sergio Penkale (Applied Language Solutions, UK) > Juan Antonio P?rez-Ortiz (Universitat d'Alacant, Spain) > Maja Popovi? (DFKI, Bermany) > Felipe S?nchez-Mart?nez (Universitat d'Alacant, Spain) > Kepa Sarasola (Euskal Herriko Unibertsitatea, Spain) > Michel Simard (National Research Council, Canada) > Sara Stymne (Link?ping University, Sweden) > J?rg Tiedemann (Uppsala University, Sweden) > John Tinsley (Dublin City University, Ireland) > Jun-Ichi Tsujii (Microsoft Research Asia, China) > Vincent Vandeghinste (Katholieke Universiteit Leuven, Belgium) > Fran?ois Yvon (LIMSI/CNRS, France) > > User track: > > Juan Alberto Alonso (Lucy Software Ib?rica, Spain) > Diego Bartolome (Tau You, Spain) > Anthony Clarke ? (CLS Communications AG., Switzerland) > David Clarke (WeLocalize, Ireland) > Heidi Depraetere (Cross Language, Belgium) > Mike Dillinger (Translation Optimization Partners, US) > Ray Flournoy (Adobe Systems, US) > Viggo Hansen (EAMT Executive Committee) > Manuel Herranz (PangeaMT, Spain) > Fred ?Hollowood ? ?(Symantec, Ireland) > Daniel Grasmick (Lucy Software, Germany) > Dorothy Kenny (Dublin City University) > Bente Maegaard, CST (University of Copenhagen, Denmark) > Enda Mcdonnell (Alchemy Software, Ireland) > Nelson Ng ?(Ebay, US) > Sharon O'Brien (Dublin City University) > Sergio Ortiz-Rojas ?(Prompsit Language Engineering, Spain) > Mirko Plitt ?(Autodesk, Switzerland) > Gema Ramirez Sanchez (Prompsit Language Engineering, Spain) > Adriane Rinsche (Language Technology Centre, UK) > Phil Ritchie (VistaTEC, Ireland) > Johann Roturier (Symantec, Ireland) > Reinhard Schaeler (University of Limerick, Ireland) > Dag Schmidtke ? (Microsoft Ireland, Dublin, Ireland) > J?rg Sch?tz (Bioloom, Germany) > Svetlana Sheremetyeva (LanA Consulting ApS, Denmark) > Svetlana Sokolova ?(PROMT, Russia) > Gregor Thurmair ?(Linguatec, Germany) > Feiyu Xu (DFKI, Germany) > Elia Yuste (PangeaMT, Spain) > Ventsislav Zhechev (Autodesk, Switzerland) > > ?------------------------------ Questions? ------------------------------ > > For more details, please visit the conference website: > http://eamt2012.fbk.eu/ > > > > ------------------------------ > > Message: 3 > Date: Fri, 20 Jan 2012 14:11:31 +0000 > From: Guchun Zhang <[email protected]> > Subject: Re: [Moses-support] Incremental training > To: [email protected] > Message-ID: > <ca+cfsvln6xdq3hr6ym_okkhhnrfcteoo9f8ldq_w5mjt_z5...@mail.gmail.com > > > Content-Type: text/plain; charset="iso-8859-1" > > Hi again, > > I got the config file done as suggested by the sample config file. However, > I received a few errors regarding the parameters set in the config file. > > ERROR: parameter 'stepk' does not exist. > ERROR: Unrecognized attribute :step_k: > ERROR: parameter 'oldtrprbs' does not exist. > ERROR: Unrecognized attribute :oldTrPrbs: > ERROR: parameter 'oldalprbs' does not exist. > ERROR: Unrecognized attribute :oldAlPrbs: > > I couldn't find these parameter names in the manual of GIZA++. But I also > didn't find an entry for 'coocurrencefile'. > > Am I missing some tricks here? > > Also a Segmentation Fault crashed GIZA++ after > > ----------- > Model1: Iteration 1 > Reading more sentence pairs into memory ... > Segmentation fault > > Any help or advice is greatly appreciated. > > Cheers, > > Guchun > > > On 20 January 2012 09:54, Guchun Zhang <[email protected]> wrote: > > > Cheers. > > > > Guchun > > > > > > On 20 January 2012 03:26, Qin Gao <[email protected]> wrote: > > > >> These are lexical translation and distortion models produced by previous > >> training, and can be produced by removing -nodump and -onlyaldumps from > >> giza options in moses training scripts. > >> > >> For documentation of giza and mgiza parameters, you can refer to > >> > >> http://geek.kyloo.net/software/doku.php/mgiza:configure > >> > >> Best, > >> --Q > >> > >> > >> > >> On Thu, Jan 19, 2012 at 9:10 PM, Philipp Koehn <[email protected] > >wrote: > >> > >>> Hi, > >>> > >>> these are paths to the model files produced > >>> for the original (not-updated) model. > >>> > >>> -phi > >>> > >>> On Thu, Jan 19, 2012 at 9:36 AM, Guchun Zhang <[email protected] > >wrote: > >>> > >>>> Hi, > >>>> > >>>> I am trying out incremental training. I am stuck in the Update and > >>>> Compute Alignments stage. In the sample config file for GIZA++, I am > not > >>>> quite sure what are the following parameters > >>>> > >>>> oldTrPrbs: <path-to-original-thmm> (old translation probabilities?) > >>>> oldAlPrbs: <path-to-original-hhmm> (old alignment probabilities?) > >>>> > >>>> and where are the files they ask for? > >>>> > >>>> Many thanks, > >>>> > >>>> Guchun > >>>> > >>>> _______________________________________________ > >>>> Moses-support mailing list > >>>> [email protected] > >>>> http://mailman.mit.edu/mailman/listinfo/moses-support > >>>> > >>>> > >>> > >>> _______________________________________________ > >>> Moses-support mailing list > >>> [email protected] > >>> http://mailman.mit.edu/mailman/listinfo/moses-support > >>> > >>> > >> > > > -------------- next part -------------- > An HTML attachment was scrubbed... > URL: > http://mailman.mit.edu/mailman/private/moses-support/attachments/20120120/d72eaa9e/attachment.htm > > ------------------------------ > > _______________________________________________ > Moses-support mailing list > [email protected] > http://mailman.mit.edu/mailman/listinfo/moses-support > > > End of Moses-support Digest, Vol 63, Issue 31 > ********************************************* > >
_______________________________________________ Moses-support mailing list [email protected] http://mailman.mit.edu/mailman/listinfo/moses-support
