%0 Journal Article %1 resnik2003parallel %A Resnik, Philip %A Smith, Noah A. %C Cambridge, MA, USA %D 2003 %I MIT Press %J Computational Linguistics %K corpus language linguistics web alexandria %N 3 %P 349--380 %R 10.1162/089120103322711578 %T The Web as a parallel corpus %U http://dx.doi.org/10.1162/089120103322711578 %V 29 %X Parallel corpora have become an essential resource for work in multilingual natural language processing. In this article, we report on our work using the STRAND system for mining parallel text on the World Wide Web,first reviewing the original algorithm and results and then presenting a set of significant enhancements. These enhancements include the use of supervised learning based on structural features of documents to improve classification performance, a new content-based measure of translational equivalence, and adaptation of the system to take advantage of the Internet Archive for mining parallel text from the Web on a large scale. Finally, the value of these techniques is demonstrated in the construction of a significant parallel corpus for a low-density language pair.

@article{resnik2003parallel, abstract = {Parallel corpora have become an essential resource for work in multilingual natural language processing. In this article, we report on our work using the STRAND system for mining parallel text on the World Wide Web,first reviewing the original algorithm and results and then presenting a set of significant enhancements. These enhancements include the use of supervised learning based on structural features of documents to improve classification performance, a new content-based measure of translational equivalence, and adaptation of the system to take advantage of the Internet Archive for mining parallel text from the Web on a large scale. Finally, the value of these techniques is demonstrated in the construction of a significant parallel corpus for a low-density language pair.}, acmid = {964753}, added-at = {2012-09-26T17:03:46.000+0200}, address = {Cambridge, MA, USA}, author = {Resnik, Philip and Smith, Noah A.}, biburl = {https://www.bibsonomy.org/bibtex/22fdc5044a0d669f6766edaaceaae2bc3/jaeschke}, doi = {10.1162/089120103322711578}, interhash = {b23f5b4586fb7dd07c28c376b08c0eda}, intrahash = {2fdc5044a0d669f6766edaaceaae2bc3}, issn = {0891-2017}, issue_date = {September 2003}, journal = {Computational Linguistics}, keywords = {corpus language linguistics web alexandria}, month = sep, number = 3, numpages = {32}, pages = {349--380}, publisher = {MIT Press}, timestamp = {2014-07-28T15:57:31.000+0200}, title = {The Web as a parallel corpus}, url = {http://dx.doi.org/10.1162/089120103322711578}, volume = 29, year = 2003 }