@article{klein_error_1998,
	title = {Error tolerant document structure analysis},
	volume = {1},
	url = {https://link-springer-com.libproxy.unl.edu/article/10.1007/s007990050028},
	abstract = {Successful applications of digital libraries require structured access to sources of information. This paper presents an approach to extract the logical structure of text documents. The extracted structure is explicated by means of SGML (Standard Generalized Markup Language). Consequently, the extraction is achieved on the basis of grammars that extend SGML with recognition rules. From these grammars parsing automata are generated. These automata are used to partition a flat text document into its elements, to discard formatting information, and to insert SGML markups. Complex document structures and fallback rules needed for error tolerant parsing make such automata highly ambiguous. A novel parsing strategy has been developed that ranks and prunes ambiguous parsing paths.},
	number = {4},
	urldate = {2017-09-26},
	journal = {International Journal on Digital Libraries},
	author = {Klein, Bertin and Fankhauser, Peter},
	month = mar,
	year = {1998},
	pages = {344--357},
}

{"_id":"P9BZrvwbTQ24Fq9C6","bibbaseid":"klein-fankhauser-errortolerantdocumentstructureanalysis-1998","author_short":["Klein, B.","Fankhauser, P."],"bibdata":{"bibtype":"article","type":"article","title":"Error tolerant document structure analysis","volume":"1","url":"https://link-springer-com.libproxy.unl.edu/article/10.1007/s007990050028","abstract":"Successful applications of digital libraries require structured access to sources of information. This paper presents an approach to extract the logical structure of text documents. The extracted structure is explicated by means of SGML (Standard Generalized Markup Language). Consequently, the extraction is achieved on the basis of grammars that extend SGML with recognition rules. From these grammars parsing automata are generated. These automata are used to partition a flat text document into its elements, to discard formatting information, and to insert SGML markups. Complex document structures and fallback rules needed for error tolerant parsing make such automata highly ambiguous. A novel parsing strategy has been developed that ranks and prunes ambiguous parsing paths.","number":"4","urldate":"2017-09-26","journal":"International Journal on Digital Libraries","author":[{"propositions":[],"lastnames":["Klein"],"firstnames":["Bertin"],"suffixes":[]},{"propositions":[],"lastnames":["Fankhauser"],"firstnames":["Peter"],"suffixes":[]}],"month":"March","year":"1998","pages":"344–357","bibtex":"@article{klein_error_1998,\n\ttitle = {Error tolerant document structure analysis},\n\tvolume = {1},\n\turl = {https://link-springer-com.libproxy.unl.edu/article/10.1007/s007990050028},\n\tabstract = {Successful applications of digital libraries require structured access to sources of information. This paper presents an approach to extract the logical structure of text documents. The extracted structure is explicated by means of SGML (Standard Generalized Markup Language). Consequently, the extraction is achieved on the basis of grammars that extend SGML with recognition rules. From these grammars parsing automata are generated. These automata are used to partition a flat text document into its elements, to discard formatting information, and to insert SGML markups. Complex document structures and fallback rules needed for error tolerant parsing make such automata highly ambiguous. A novel parsing strategy has been developed that ranks and prunes ambiguous parsing paths.},\n\tnumber = {4},\n\turldate = {2017-09-26},\n\tjournal = {International Journal on Digital Libraries},\n\tauthor = {Klein, Bertin and Fankhauser, Peter},\n\tmonth = mar,\n\tyear = {1998},\n\tpages = {344--357},\n}\n\n","author_short":["Klein, B.","Fankhauser, P."],"key":"klein_error_1998","id":"klein_error_1998","bibbaseid":"klein-fankhauser-errortolerantdocumentstructureanalysis-1998","role":"author","urls":{"Paper":"https://link-springer-com.libproxy.unl.edu/article/10.1007/s007990050028"},"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://api.zotero.org/groups/2222059/items?key=4nm7ZpgsFBnBcdCT39DfwgfD&format=bibtex&limit=100","dataSources":["JKk9Lj5RvZeme63gg"],"keywords":[],"search_terms":["error","tolerant","document","structure","analysis","klein","fankhauser"],"title":"Error tolerant document structure analysis","year":1998}