In this article, we address the problem of text passage alignment across interlingual article pairs in Wikipedia. We develop methods that enable the identification and interlinking of text passages written in different languages and containing overlapping information. Interlingual text passage alignment can enable Wikipedia editors and readers to better understand language-specific context of entities, provide valuable insights in cultural differences, and build a basis for qualitative analysis of the articles. An important challenge in this context is the tradeoff between the granularity of the extracted text passages and the precision of the alignment. Whereas short text passages can result in more precise alignment, longer text passages can facilitate a better overview of the differences in an article pair. To better understand these aspects from the user perspective, we conduct a user study at the example of the German, Russian, and English Wikipedia and collect a user-annotated benchmark. Then we propose MultiWiki, a method that adopts an integrated approach to the text passage alignment using semantic similarity measures and greedy algorithms and achieves precise results with respect to the user-defined alignment. The MultiWiki demonstration is publicly available and currently supports four language pairs.
%0 Journal Article
%1 Gottschalk:2017:MIT:3062397.3004296
%A Gottschalk, Simon
%A Demidova, Elena
%C New York, NY, USA
%D 2017
%I ACM
%J ACM Trans. Web
%K alexandria wikipedia
%N 1
%P 6:1--6:30
%R 10.1145/3004296
%T MultiWiki: Interlingual Text Passage Alignment in Wikipedia
%U http://doi.acm.org/10.1145/3004296
%V 11
%X In this article, we address the problem of text passage alignment across interlingual article pairs in Wikipedia. We develop methods that enable the identification and interlinking of text passages written in different languages and containing overlapping information. Interlingual text passage alignment can enable Wikipedia editors and readers to better understand language-specific context of entities, provide valuable insights in cultural differences, and build a basis for qualitative analysis of the articles. An important challenge in this context is the tradeoff between the granularity of the extracted text passages and the precision of the alignment. Whereas short text passages can result in more precise alignment, longer text passages can facilitate a better overview of the differences in an article pair. To better understand these aspects from the user perspective, we conduct a user study at the example of the German, Russian, and English Wikipedia and collect a user-annotated benchmark. Then we propose MultiWiki, a method that adopts an integrated approach to the text passage alignment using semantic similarity measures and greedy algorithms and achieves precise results with respect to the user-defined alignment. The MultiWiki demonstration is publicly available and currently supports four language pairs.
@article{Gottschalk:2017:MIT:3062397.3004296,
abstract = {In this article, we address the problem of text passage alignment across interlingual article pairs in Wikipedia. We develop methods that enable the identification and interlinking of text passages written in different languages and containing overlapping information. Interlingual text passage alignment can enable Wikipedia editors and readers to better understand language-specific context of entities, provide valuable insights in cultural differences, and build a basis for qualitative analysis of the articles. An important challenge in this context is the tradeoff between the granularity of the extracted text passages and the precision of the alignment. Whereas short text passages can result in more precise alignment, longer text passages can facilitate a better overview of the differences in an article pair. To better understand these aspects from the user perspective, we conduct a user study at the example of the German, Russian, and English Wikipedia and collect a user-annotated benchmark. Then we propose MultiWiki, a method that adopts an integrated approach to the text passage alignment using semantic similarity measures and greedy algorithms and achieves precise results with respect to the user-defined alignment. The MultiWiki demonstration is publicly available and currently supports four language pairs.},
acmid = {3004296},
added-at = {2017-05-15T11:20:33.000+0200},
address = {New York, NY, USA},
articleno = {6},
author = {Gottschalk, Simon and Demidova, Elena},
biburl = {https://www.bibsonomy.org/bibtex/27d0f31edbb6a111f3633623c423e1864/alexandriaproj},
doi = {10.1145/3004296},
interhash = {8cf89d374aabb586687bc6a6a5ad9488},
intrahash = {7d0f31edbb6a111f3633623c423e1864},
issn = {1559-1131},
issue_date = {April 2017},
journal = {ACM Trans. Web},
keywords = {alexandria wikipedia},
month = apr,
number = 1,
numpages = {30},
pages = {6:1--6:30},
publisher = {ACM},
timestamp = {2017-05-15T11:20:33.000+0200},
title = {MultiWiki: Interlingual Text Passage Alignment in Wikipedia},
url = {http://doi.acm.org/10.1145/3004296},
volume = 11,
year = 2017
}