Paraphrasing and Translation - part 10 potx

170 Appendix B. Example Translations SOURCE REFERENCE BASELINE SYSTEM PARAPHRASE SYSTEM sin embargo , hay aspectos y cuestiones de envergadura de los que disentimos . however , there are aspects and questions of significance that we disagree on . however , there are issues and issues of content of the disenti- mos . however , there are aspects and content of the issues that we do not agree . se me ha encomendado la misi ´ on de ser ponente en relaci ´ on con estonia . i have been entrusted with the task of acting as rapporteur where estonia is concerned . i encomendado has the task of being rapporteur in connection with estonia . i was given the task of being rapporteur in connection with estonia . no podemos darnos el lujo de perder ocasiones como las que hubo a comienzos de los a ˜ nos 90 . we cannot afford to lose more of the momentum that existed at the beginning of the nineties . we cannot understand luxury of losing occasions as there was at the beginning of the 90 years . we cannot afford to lose occa- sions as there was at the begin- ning of the 90 years . la democracia no es solamente una cuesti ´ on de mayor ´ ıas sino sobre todo de una codecisi ´ on equilibrada de las minor ´ ıas . democracy is not just about ma- jorities , more than anything it is about minorities being given commensurate codecision pow- ers . democracy is not just a ques- tion of mayor ´ ıas but above all a codecision balanced of minori- ties . democracy is not just a ques- tion of majority but above all a codecision balanced of minori- ties . no nos podemos dejar cegar por los porcentajes de derecho comunitario recogidos en la leg- islaci ´ on nacional . we should not be blinded by the percentage figures of com- munity law transposed into na- tional legislation . we can make cegar by the por- centajes of community law in- corporated into national legisla- tion . we cannot be reduced by the percentage of community law incorporated into national legis- lation . Table B.3: Example translations from the baseline and paraphrase systems when trained on a Spanish-English corpus with 40,000 sentence pairs 171 SOURCE REFERENCE BASELINE SYSTEM PARAPHRASE SYSTEM tiene que ser un acuerdo que impulse la cooperacin pesquera y el sector pesquero marroqu ´ ı , pero que satisfaga tambin ple- namente los intereses pesqueros de las flotas europeas . it must be an agreement which provides an impetus for fish- eries cooperation and the moroc- can fishing industry , but which also fully satisfies the fisheries interests of the european fleets . it has to be a cooperation agree- ment impulse fisheries and the moroccan fisheries sector , but also satisfaga fully the interests of the european fisheries fleets . it has to be an agreement which pursue cooperation fishing and the moroccan fisheries sector , but we also fully satisfy the fishing interests of the european fleets . francia , por su lado , posee de- partamentos de ultramar en el oc ´ eano ´ ındico y el caribe . france , on the other hand , owns overseas departments in the in- dian ocean and the caribbean . france , for its part , has ultra- mar departments of the oc ´ eano ´ ındico and the caribe . france , for its part , has the de- partments in the indian ocean and the caribbean . desear ´ ıa concluir , simplemente , mencionando tres problemas que han surgido . i would like to conclude simply by mentioning three problems which have come up . i would like to conclude , simply , mencionando three problems that have emerged . i would like to conclude , this is simply mentioning three prob- lems which have arisen . hay que tratar de remover todas las causas de aprovechamiento existentes buscando y persigu- iendo a quien se ha aprovechado , ha abusado de las pobla- ciones que se hallan en estado de necesidad . we should try to remove all the existing causes of exploitation , identifying and bringing to justice those who have abused peoples which are in a state of need . we must deal with remover all the causes of existing buscando exploitation and to pursue to anyone who has used this oppor- tunity , has has abusado of peo- ple who have chosen a state of need . we must try to eliminate all the causes of exploitation and pur- suing existing seeking to anyone who has abused people who are in a state of need . la aut ´ entica sorpresa de este pre- supuesto se refiere a las ac- ciones exteriores donde domina el ego ´ ısmo . the real surprise in this bud- get relates to external actions , where selfishness is the rule . the real surprise this budget re- lates to the external action dom- ina where the ego ´ ısmo . the real surprise this budget re- lates to the external actions , where the dominant selfishness . Table B.4: Example translations from the baseline and paraphrase systems when trained on a Spanish-English corpus with 80,000 sentence pairs 172 Appendix B. Example Translations SOURCE REFERENCE BASELINE SYSTEM PARAPHRASE SYSTEM basta con que miremos a nue- stros televisores y veamos las dificultades actuales en el ori- ente medio para que lo recorde- mos todos los d ´ ıas . we only have to look at our tele- vision sets to see the difficul- ties in the middle east to be re- minded of that each and every day . it is enough to look at our tele- visores and see the present dif- ficulties in the middle east for what it every day . it is enough to look to our televi- sion and see the present difficul- ties in the middle east to remind you that every day . pero he captado perfecta- mente que m ´ as all ´ a del aspecto ling ¨ u ´ ıstico , su pregunta esconde otra preocupaci ´ on . but i understand that , behind the linguistic aspect , your ques- tion expresses another concern . but i captado well beyond the linguistic aspect , your question hides another concern . but i understand perfectly well that beyond the linguistic aspect , your question hides another concern . eso demuestra que la comisi ´ on no permaneci ´ o inactiva y que llev ´ o a efecto las observaciones que ustedes han formulado . this shows that the commission has not been idle and that it is acting on the comments that you have made . this demonstrates that the com- mission permaneci ´ o not been idle and led to effect the remarks that you have raised . this demonstrates that the com- mission has not been idle and that led to effect the remarks that you have put forward . nos referimos en particular al nuevo proyecto piloto que fi- nanciar ´ a acciones de infor- maci ´ on en materia de lucha con- tra la pederastia . we refer in particular to the new pilot scheme to finance infor- mation measures in the fight against paedophilia . we are referring in particular the new pilot project which fi- nanciar ´ a information actions to combat paedophilia . we are referring in particular to the new pilot project to fund ac- tions of information in the fight against paedophilia . en lo referente al procedimiento disciplinario no unas reglas claras se deben aplicar dichas re- glas . y tampoco la cuesti ´ on de la externalizaci ´ on est ´ a definiti- vamente aclarada . as for disciplinary procedures , no clear rules have been formu- lated so far as to how such rules would be enforced , nor has the question of external agencies been conclusively resolved . with regard to the procedure dis- ciplinario not yet clear rules on how they should apply these rules , and also the question of the externalizaci ´ on is definitely aclarada . as far as the disciplinary proce- dure but so far not clear rules on how these rules must apply ei- ther , nor the question of the del- egation is quite clear . Table B.5: Example translations from the baseline and paraphrase systems when trained on a Spanish-English corpus with 160,000 sentence pairs 173 SOURCE REFERENCE BASELINE SYSTEM PARAPHRASE SYSTEM resulta que en los ´ ultimos tiem- pos ese parlamento ha sido v ´ ıctima de algunos equ ´ ıvocos e incluso de algunas cr ´ ıticas . the central american parliament appears to have recently been the subject of certain misunder- standings and even criticism . it is that in recent times that par- liament has been the victim of some equ ´ ıvocos and even some criticisms . it is that in recent times that par- liament has been the victim of some misunderstandings and even some criticisms . la pol ´ ıtica econ ´ omica y so- cial de la ue ha conducido a la reducci ´ on de la capacidad adquisitiva de los trabajadores . the economic and social policy of the eu has resulted in the reduced purchasing power of workers . the economic and social policy of the eu has led to the reduc- tion in capacity adquisitiva of workers . the economic and social policy of the eu has led to the reduction of buying power of workers . la lucha contra la exclusi ´ on so- cial queda relegada al rango de la asistencia . the fight against social exclusion is relegated to the level of assis- tance . the fight against social exclusion is relegada the rank of assis- tance . the fight against social exclusion is relegated to the status of the assistance . los interlocutores sociales se en- cuentran en la posici ´ on m ´ as favorable para proponer solu- ciones practicables . the social partners are in the best place to work out viable solu- tions . the social partners are in the more favourable position to pro- pose solutions practicables . the social partners are in the more favourable position to pro- pose practical solutions . en lo relativo a los descrip- tores , como “bajo contenido en alquitr ´ an” , “suave” y “light” , todav ´ ıa me sigue pareciendo que son enga ˜ nosos , y por eso estoy en contra de las enmiendas . i still feel that messages such as ‘low-tar’ , ‘mild’ and ‘light’ are misleading , so i will , in fact , oppose the amendments . with regard to the descriptores , as “low tar content in” , “soft” and “light” , there is still that are enga ˜ nosos , and i am therefore against the amendments . with regard to the descriptores , as ‘low tar content in’ , ‘mild’ and ‘light’ , there is still are mis- leading , and that is why i am against the amendments . Table B.6: Example translations from the baseline and paraphrase systems when trained on a Spanish-English corpus with 320,000 sentence pairs Bibliography Satanjeev Banerjee and Alon Lavie (2005). Meteor: An automatic metric for MT eval- uation with improved correlation with human judgments. In Workshop on Intrin- sic and Extrinsic Evaluation Measures for MT and/or Summarization, Ann Arbor, Michigan. Colin Bannard and Chris Callison-Burch (2005). Paraphrasing with bilingual parallel corpora. In Proceedings of the 43rd Annual Meeting of the Association for Compu- tational Linguistics (ACL-2005), Ann Arbor, Michigan. Regina Barzilay (2003). Information Fusion for Mutlidocument Summarization: Para- phrasing and Generation. PhD thesis, Columbia University, New York. Regina Barzilay and Lillian Lee (2003). Learning to paraphrase: An unsupervised approach using multiple-sequence alignment. In Proceedings of the Human Lan- guage Technology Conference of the North American chapter of the Association for Computational Linguistics (HLT/NAACL-2003), Edmonton, Alberta. Regina Barzilay and Kathleen McKeown (2001). Extracting paraphrases from a par- allel corpus. In Proceedings of the 39th Annual Meeting of the Association for Computational Linguistics (ACL-2001), Toulouse, France. Dan Bikel (2002). Design of a multi-lingual, parallel-processing statistical parsing engine. In Proceedings of Second International Conference on Human Language Technology Research (HLT-02), San Diego, California. Alexandra Birch, Chris Callison-Burch, and Miles Osborne (2006). Constraining the phrase-based, joint probability statistical translation model. In Proceedings of the 7th Biennial Conference of the Association for Machine Translation in the Americas (AMTA-2006), Cambridge, Massachusetts. 175 176 Bibliography Phil Blunsom and Trevor Cohn (2006). Discriminative word alignment with condi- tional random fields. In Proceedings of the 21st International Conference on Com- putational Linguistics and 44th Annual Meeting of the Association for Computa- tional Linguistics (ACL-CoLing-2006), Sydney, Australia. Peter Brown, John Cocke, Stephen Della Pietra, Vincent Della Pietra, Frederick Je- linek, Robert Mercer, and Paul Poossin (1988). A statistical approach to lan- guage translation. In 12th International Conference on Computational Linguistics (CoLing-1988). Peter Brown, John Cocke, Stephen Della Pietra, Vincent Della Pietra, Frederick Je- linek, Robert Mercer, and Paul Poossin (1990). A statistical approach to language translation. Computational Linguistics, 16(2). Peter Brown, Stephen Della Pietra, Vincent Della Pietra, and Robert Mercer (1991). A statistical approach to sense disambiguation in machine translation. In Workshop on Human Language Technology, pages 146–151. Peter Brown, Stephen Della Pietra, Vincent Della Pietra, and Robert Mercer (1993). The mathematics of machine translation: Parameter estimation. Computational Lin- guistics, 19(2):263–311. Chris Callison-Burch, Colin Bannard, and Josh Schroeder (2005). Scaling phrase- based statistical machine translation to larger corpora and longer phrases. In Pro- ceedings of the 43rd Annual Meeting of the Association for Computational Linguis- tics (ACL-2005), Ann Arbor, Michigan. Chris Callison-Burch, Cameron Fordyce, Philipp Koehn, Christof Monz, and Josh Schroeder (2007). (Meta-) evaluation of machine translation. In Proceedings of the Second Workshop on Statistical Machine Translation, pages 136–158, Prague, Czech Republic. Association for Computational Linguistics. Chris Callison-Burch, Philipp Koehn, and Miles Osborne (2006a). Improved statisti- cal machine translation using paraphrases. In Proceedings of the Human Language Technology Conference of the North American chapter of the Association for Com- putational Linguistics (HLT/NAACL-2006), New York, New York. Chris Callison-Burch, Miles Osborne, and Philipp Koehn (2006b). Re-evaluating the role of Bleu in machine translation research. In 11th Conference of the European Bibliography 177 Chapter of the Association for Computational Linguistics (EACL-2006), Trento, Italy. Chris Callison-Burch, David Talbot, and Miles Osborne (2004). Statistical machine translation with word- and sentence-aligned parallel corpora. In Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics (ACL-2004), Barcelona, Spain. Michael Carl and Andy Way (2003). Recent Advances in Example-Based Machine Translation. Springer. Colin Cherry and Dekang Lin (2003). A probability model to improve word alignment. In Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics (ACL-2003), Sapporo, Japan. David Chiang (2007). Hierarchical phrase-based translation. Computational Linguis- tics, 33(2):201–228. Philip Clarkson and Roni Rosenfeld (1997). Statistical language modeling using the CMU-Cambridge toolkit. In Proceedings ESCA Eurospeech. Deborah Coughlin (2003). Correlating automated and human assessments of machine translation quality. In Proceedings of MT Summit IX, New Orleans, Louisiana. Ido Dagan and Alon Itai (1994). Word sense disambiguation using a second language monolingual corpus. Computational Linguistics, 20(4):563–596. Tiphaine Dalmas (2007). Information Fusion for Automated Question Answering. PhD thesis, University of Edinburgh, Scotland. Adri ` a de Gispert, Jos ` e B. Marino, and Josep M. Crego (2005). Improving statistical machine translation by classifying and generalizing inflected verb forms. In Pro- ceedings of 9th European Conference on Speech Communication and Technology. A. P. Dempster, N. M. Laird, and D. B. Rubin (1977). Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society, 39(1):1–38. Mona Diab (2000). An unsupervised method for word sense tagging using parallel corpora: A preliminary investigation. In Proceedings of Special Interest Group in Lexical Semantics (SIGLEX) Workshop. 178 Bibliography Mona Diab and Philip Resnik (2002). An unsupervised method for word sense tagging using parallel corpora. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL-2002), Philadelphia, Pennsylvania. George Doddington (2002). Automatic evaluation of machine translation quality us- ing n-gram co-occurrence statistics. In Human Language Technology: Notebook Proceedings, pages 128–132, San Diego, California. Bill Dolan and Chris Brockett (2005). Automatically constructing a corpus of senten- tial paraphrases. In Proceedings of 3rd International Workshop on Paraphrasing. Bill Dolan, Chris Quirk, and Chris Brockett (2004). Unsupervised construction of large paraphrase corpora: Exploiting massively parallel news sources. In Proceedings of the 20th International Conference on Computational Linguistics. Mark Dras (1997). Representing paraphrases using synchronous tree adjoining gram- mars. In 35tg Annual Meeting of the Association for Computational Linguistics (ACL-1997), Madrid, Spain. Mark Dras (1999a). A meta-level grammar: Redefining synchronous TAGs for trans- lation and paraphrase. In Proceedings of the 37th Annual Meeting of the Association for Computational Linguistics (ACL), pages 98–104, Hong Kong. Mark Dras (1999b). Tree Adjoining Grammar and the Reluctant Paraphrasing of Text. PhD thesis, Macquarie University, Australia. Pablo Ariel Duboue and Jennifer Chu-Carroll (2006). Answering the question you wished they had asked: The impact of paraphrasing for question answering. In Proceedings of the Human Language Technology Conference of the North American chapter of the Association for Computational Linguistics (HLT/NAACL-2006), New York, New York. Helge Dyvik (1998). Translations as semantic mirrors. In Workshop on Multilinguality and the Lexicon, pages 24–44. Alexander Fraser and Daniel Marcu (2006). Semi-supervised training for statistical word alignment. In Proceedings of the 21st International Conference on Compu- tational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics (ACL-CoLing-2006), Sydney, Australia. Bibliography 179 William Gale and Kenneth Church (1993). A program for aligning sentences in bilin- gual corpora. Compuatational Linguistics, 19(1):75–90. Sharon Goldwater and David McClosky (2005). Improving statistical MT through morphological analysis. In Proceedings of the 2005 Conference on Empirical Meth- ods in Natural Language Processing (EMNLP-2005), Vancouver, British Columbia., Canada. Zellig Harris (1954). Distributional structure. Word, 10(2-3):146–162. Eduard Hovy and Deepak Ravichandran (2003). Holy and unholy grails. Panel Dis- cussion at MT Summit IX. Ali Ibrahim, Boris Katz, and Jimmy Lin (2003). Extracting structural paraphrases from aligned monolingual corpora. In Proceedings of the Second International Workshop on Paraphrasing (ACL 2003). Nancy Ide (2000). Cross language sense determination: Can it work? Computers and the Humanities: Sepcail Issue on SENSEVAL, 34:15–48. Lidija Iordanskaja, Richard Kittredge, and Alain Polg ´ ere (1991). Lexical selection and paraphrase in a meaning text generation model. In C ´ ecile L. Paris, William R. Swartout, and William C. Mann, editors, Natural Language Generation in Artificial Intelligence and Computational Linguistics. Kluwer Academic. Abraham Ittycheriah and Salim Roukos (2005). A maximum entropy word aligner for arabic-english machine translation. In Proceedings of the 2005 Conference on Empirical Methods in Natural Language Processing (EMNLP-2005), Vancouver, British Columbia., Canada. Hiroshi Kanayama (2003). Paraphrasing rules for automatic evaluation of translation into japanese. In Proceedings of the Second International Workshop on Paraphras- ing (ACL 2003), Sapporo, Japan. David Kauchak and Regina Barzilay (2006). Paraphrasing for automatic evaluation. In Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing (EMNLP-2006), Sydney, Australia. Katrin Kirchhoff, Mei Yang, and Kevin Duh (2006). Machine translation of parlia- mentary proceedings using morpho-syntactic knowledge. In Proceedings of the TC- STAR Workshop on Speech-to-Speech Translation. [...]... machine translation In Proceedings of MT-Summit, Phuket, Thailand Philipp Koehn, Amittai Axelrod, Alexandra Birch, Chris Callison-Burch, Miles Osborne, David Talbot, and Michael White (2005a) Edinburgh system description for the 2005 IWSLT speech translation evaluation In Proceedings of International Workshop on Spoken Language Translation Philipp Koehn, Amittai Axelrod, Alexandra Birch, Chris Callison-Burch,... Franz Josef Och and Hermann Ney (2004) The alignment template approach to statistical machine translation Computational Linguistics, 30(4):417–449 Karolina Owczarzak, Declan Groves, Josef Van Genabith, and Andy Way (2006) Contextual bitext-derived paraphrases in automatic mt evaluation In Proceedings of the SMT Workshop at HLT-NAACL Bo Pang, Kevin Knight, and Daniel Marcu (2003) Syntax-based alignment... (ACL-2002), Philadelphia, Pennsylvania Mark Przybocki (2004) NIST 2004 machine translation evaluation results Confidential e-mail to workshop participants Chris Quirk, Chris Brockett, and William Dolan (2004) Monolingual machine translation for paraphrase generation In Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing (EMNLP-2004), Barcelona, Spain Deepak Ravichandran... Chapter of the Association for Computational Linguistics (EACL-2006), Trento, Italy Ying Zhang and Stephan Vogel (2004) Measuring confidence intervals for the machine translation evaluation metrics In Proceedings of the 10th International Conference on Theoretical and Methodological Issues in Machine Translation (TMI-2004) Ying Zhang, Stephan Vogel, and Alex Waibel (2004) Interpreting bleu/nist scores: How... in Natural Language Processing (EMNLP-2005), Vancouver, British Columbia., Canada Robert C Moore, Wen-Tau Yih, and Andreas Bode (2006) Improved discriminative bilingual word alignment In Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing (EMNLP-2006), Sydney, Australia Dragos Munteanu and Daniel Marcu (2005) Improving machine translation performance by exploiting... Dragos Stefan Munteanu and Daniel Marcu (2006) Extracting parallel sub-sentential fragments from comparable corpora In Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics (ACL-CoLing-2006), Sydney, Australia Makoto Nagao (1981) A framework of a mechanical translation between japanese and english by analogy... Ney (2000) An evaluation tool for machine translation: Fast evaluation for mt research In Proceedings of 2nd International Conference on Language Resources and Evaluation (LREC), Athens, Greece NIST and LDC (2007) Post editing guidelines for gale machine translation evaluation Guidelines developed by the National Institute of Standards and Technology (NIST), and the Linguistic Data Consortium (LDC)... WS-2006, Johns Hopkins University Philipp Koehn and Kevin Knight (2003) Empirical methods for compound splitting In 10th Conference of the European Chapter of the Association for Computational Linguistics (EACL-2003), Budapest, Hungary Philipp Koehn and Christof Monz (2005) Shared task: Statistical machine translation between European languages In Proceedings of ACL 2005 Workshop on Parallel Text Translation, ... Text Translation, Ann Arbor, Michigan Philipp Koehn and Christof Monz (2006) Manual and automatic evaluation of machine translation between European languages In Proceedings of NAACL 2006 Workshop on Statistical Machine Translation, New York, New York Bibliography Philipp Koehn, Franz Josef Och, and Daniel Marcu (2003) 181 Statistical phrase- based translation In Proceedings of the Human Language Technology... Satoshi Sato and Makoto Nagao (1990) Toward memory-based translation In Papers presented to the 13th International Conference on Computational Linguistics (CoLing-1990) Matthew Snover, Bonnie Dorr, Richard Schwartz, Linnea Micciulla, and John Makhoul (2006) A study of translation edit rate with targeted human annotation In Proceedings of the 7th Biennial Conference of the Association for Machine Translation . posee de- partamentos de ultramar en el oc ´ eano ´ ındico y el caribe . france , on the other hand , owns overseas departments in the in- dian ocean and the caribbean . france , for its part ,. . france , for its part , has ultra- mar departments of the oc ´ eano ´ ındico and the caribe . france , for its part , has the de- partments in the indian ocean and the caribbean . desear ´ ıa. Lin- guistics, 19(2):263–311. Chris Callison-Burch, Colin Bannard, and Josh Schroeder (2005). Scaling phrase- based statistical machine translation to larger corpora and longer phrases. In Pro- ceedings