The automatic construction of large-scale corpora for summarization research Export

@inproceedings{citeulike:3576177, abstract = {Summarization research is notorious for its lack of adequate corpora: today, there exist only a few small collections of texts whose units have been manually annotated for textual importance. Given the cost and tediousness of the annotation process, it is very unlikely that we will ever manually annotate for textual importance sufficiently large corpora of texts. To circumvent this problem, we have developed an algorithm that constructs such corpora automatically. Our algorithm takes as input an hAbstract, Texti tuple and generates the corresponding Extract, i.e., the set of clauses (sentences) in the Text that were used to write the Abstract. The performance of the algorithm is shown to be close to that of humans by means of an empirical experiment. The experiment also suggests extraction strategies that could improve the performance of automatic summarization systems.}, author = {Marcu, Daniel}, booktitle = {In Proceedings of SIGIR}, citeulike-article-id = {3576177}, citeulike-linkout-0 = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.40.8819}, keywords = {alignment, parallel-corpora, summarisation, summary-alignment, text-mining}, pages = {137--144}, posted-at = {2008-11-19 03:13:44}, priority = {2}, title = {The automatic construction of large-scale corpora for summarization research}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.40.8819}, year = {1999} }

TY - CONF ID - citeulike:3576177 L3 - citeulike-article-id:3576177 N2 - Summarization research is notorious for its lack of adequate corpora: today, there exist only a few small collections of texts whose units have been manually annotated for textual importance. Given the cost and tediousness of the annotation process, it is very unlikely that we will ever manually annotate for textual importance sufficiently large corpora of texts. To circumvent this problem, we have developed an algorithm that constructs such corpora automatically. Our algorithm takes as input an hAbstract, Texti tuple and generates the corresponding Extract, i.e., the set of clauses (sentences) in the Text that were used to write the Abstract. The performance of the algorithm is shown to be close to that of humans by means of an empirical experiment. The experiment also suggests extraction strategies that could improve the performance of automatic summarization systems. EP - 144 TI - The automatic construction of large-scale corpora for summarization research T2 - In Proceedings of SIGIR SP - 137 KW - alignment KW - parallel-corpora KW - summarisation KW - summary-alignment KW - text-mining AU - Marcu, Daniel PY - 1999/// UR - http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.40.8819 ER -