ACM Home Page
Please provide us with feedback. Feedback
Using cognates to align sentences in bilingual corpora
Full text PdfPdf (881 KB)
Source IBM Centre for Advanced Studies Conference archive
Proceedings of the 1993 conference of the Centre for Advanced Studies on Collaborative research: distributed computing - Volume 2 table of contents
Toronto, Ontario, Canada
SESSION: Documentation table of contents
Pages: 1071 - 1082  
Year of Publication: 1993
Authors
Michel Simard  Centre for Information Technologies Innovation, Laval, Québec, Canada
George F. Foster  Centre for Information Technologies Innovation, Laval, Québec, Canada
Pierre Isabelle  Centre for Information Technologies Innovation, Laval, Québec, Canada
Sponsors
: IBM Centre for Advanced Studies (CAS)
: National Research Council of Canada (NRC)
Publisher
IBM Press 
Bibliometrics
Downloads (6 Weeks): 2,   Downloads (12 Months): 20,   Citation Count: 8
Additional Information:

abstract   references   cited by   collaborative colleagues  

Tools and Actions: Review this Article  

ABSTRACT

In a recent paper, Gale and Church describe an inexpensive method for aligning bitext, based exclusively on sentence lengths [3]. While this method produces surprisingly good results (a success rate around 96%), even better results are required to perform such tasks as the computer-assisted revision of translations. In this paper, we examine some of the weaknesses of Gale and Church's program, and explain how just a small amount of linguistic knowledge would help to overcome these weaknesses. We discuss how cognates provide for a cheap and reasonably reliable source of linguistic knowledge. To illustrate this, we describe a modification to the program in which the criterion is cognates rather than sentence lengths. Finally, we show how better and more efficient results may be obtained by combining the two criteria length and "cogneteness". Our method can be generalized to accommodate other sources of linguistic knowledge, and experimentation shows that it produces better results than alignments based on length alone, at a minimal cost.



CITED BY  8
Collaborative Colleagues:
Michel Simard: colleagues
George F. Foster: colleagues
Pierre Isabelle: colleagues