1、Translation tools PATENTSCOPE search system,May 2013,Sandrine Ammann Marketing & Communications Officer,To this webinar: Translation tools in the PATENTSCOPE search system,Agenda,Latest developments Translation tools: Internet machine translation tools (Google/Microsoft) Tapta CLIR Q&A session,Addit
2、ion of the US collection,As well as PCT applications, the ARIPO, EP and LATIPAT collections,Translation tools,MT in result list,MT in description/claims/full-text,Google,Microsoft,Full-text,TAPTA,32 Technical domains from the IPC,ADMN Admin, Business, Management & Soc Sci AERO Aeronautics & Aerospac
3、e Engineering AGRI Agriculture, Fisheries & Forestry AUDV Audio, Audiovisual, Image & Video Tech AUTO Automotive & Road Vehicle Engineering BLDG Civil Engineering & Building Construction CHEM Chemical & Materials Technology DATA Computer Sci, Telecom & Broadcasting ELEC Electrical Engineering & Elec
4、tronics ENGY Energy, Fuels & Heat Transfer Eng ENVR Environmental & Safety Engineering FOOD Foods & Food Technology GENR Generalities, Language, Media & Info Sci HOME Home Contents & Household Maintenance HORO Precision Mechanics, Jewelry & Horology MANU Manufacturing & Materials Handling Tech,MARI
5、Marine Engineering MEAS Standards, Units, Metrology & Testing MECH Mechanical Engineering MEDI Medical Technology METL Metallurgy MILI Military Technology MINE Mining, Oil & Gas Extraction & Minerals NANO Nano Technology PACK Packaging & Distribution of Goods PRNT Printing & Paper RAIL Railway Engin
6、eering SCIE Optical Engineering SPRT Sports, Leisure, Tourism & Hospitality TEXT Textile & Clothing Industries TRAN Transportation,TAPTA: how does it work?,TAPTA: post-editing & exporting,How well does it work?,To evaluate machine translated text, BLEU is used.BLEU (Bilingual Evaluation Understudy)
7、is an algorithm for evaluating the quality of text which has been machine-translated from one natural language . Quality = the correspondence between a machines output and that of a human Scores are calculated for individual translated segmentsgenerally sentencesby comparing them with a set of good
8、quality reference translations.,English-French pair,15 abstracts published in March 2013 were evaluated Results: Tapta: 46.9 Google: 45.9 Google-EPO: 45.8 Microsoft : 36.7,German-English pair,11 title & abstracts published in March 2013 were evaluated. Results: BLEU: Tapta: 38.3 Google: 37.8 Microso
9、ft: 26.8 Human evaluation: adequacy/fluency: Tapta: 79% Google 65% and Microsoft 67%,English-Japanese pair,1000 segments (1 title & abstracts) published in March 2013 were evaluated. Results: BLEU: Tapta: 25.4 Google: 22.3,English-Chinese pair,1000 segments (1 title & abstracts) published in March 2
10、013 were evaluated. Results: BLEU: Tapta: 22 Google: 17.5,CLIR,CLIR stands for Cross Lingual Information Retrieval and will allow you to search a term or a phrase and its variants in:Chinese Dutch English French German Italian Japanese Korean Portuguese Russian Spanish and Swedish,CLIR: the interfac
11、e,CLIR: precision vs recall,Example: precision,Example: recall,CLIR: supervised mode,2 modes: automatic and supervisedAutomatic: 1 step Supervised: 4 steps,Automatic mode,(EN_TI:(“hearing aids“ OR “hearing prosthetic“21 OR “auditory aids“21 OR “auditory prosthetic“21) OR EN_AB:(“hearing aids“ OR “he
12、aring prosthetic“21 OR “auditory aids“21 OR “auditory prosthetic“21) OR (DE_TI:(“Hrgerte“ OR “Hrhilfegerten“) OR DE_AB:(“Hrgerte“ OR “Hrhilfegerten“) OR (ES_TI:(“audfonos“) OR ES_AB:(“audfonos“) OR (FR_TI:(“audioprothses“ OR “appareils de correction auditive“ OR “production dappareils auditifs“) OR
13、FR_AB:(“audioprothses“ OR “appareils de correction auditive“ OR “production dappareils auditifs“) OR (JA_TI:(“穴形補聴器“) OR JA_AB:(“穴形補聴器“) OR (KO_TI:(“) OR KO_AB:(“) OR (PT_TI:(“audiofone“ OR “auxlio de audio“) OR PT_AB:(“audiofone“ OR “auxlio de audio“) OR (RU_TI:(“ “22 OR “ “22 OR “ “22 OR “ “22 OR
14、“ “22 OR “ “22 OR “ “22 OR “ “22 OR “ “22) OR RU_AB:(“ “22 OR “ “22 OR “ “22 OR “ “22 OR “ “22 OR “ “22 OR “ “22 OR “ “22 OR “ “22) OR (ZH_TI:(“助听器“) OR ZH_AB:(“助听器“),Automatic mode: results,Supervised mode: 1 of 4 steps,Supervised mode : 2 of 4 steps,Supervised mode : 3 of 4 steps,Supervised mode :
15、 4 of 4 steps,Supervised mode: results,Search examples: clothes for sport,Entering “sports clothes” in the Simple search interface will return 11 resultsEntering “sports clothes” in the CLIR interface (in automatic mode) will return 791 resultsEntering “sports clothes” in the CLIR interface (in supervised mode) will return 455 results,Slides and recording,www.wipo.int/patentscope/en/webinar/index.html,+,patentscopewipo.int,mulumesc,mulumesc,
